Quantize to FP8
Browse files- Dockerfile +3 -0
- config.json +20 -1
- generation_config.json +1 -1
- main.py +52 -6
- model-00002-of-00008.safetensors +0 -3
- model-00003-of-00008.safetensors +0 -3
- model-00004-of-00008.safetensors +0 -3
- model-00005-of-00008.safetensors +0 -3
- model-00006-of-00008.safetensors +0 -3
- model-00007-of-00008.safetensors +0 -3
- model-00008-of-00008.safetensors +0 -3
- model-00001-of-00008.safetensors → model.safetensors +2 -2
- model.safetensors.index.json +0 -909
- quantize.py +105 -0
- requirements.txt +2 -0
- tokenizer_config.json +2 -1
Dockerfile
CHANGED
|
@@ -11,6 +11,9 @@ WORKDIR /app
|
|
| 11 |
# Copy requirements and install
|
| 12 |
COPY requirements.txt .
|
| 13 |
RUN pip install --no-cache-dir -r requirements.txt
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
# Copy application code
|
| 16 |
COPY main.py .
|
|
|
|
| 11 |
# Copy requirements and install
|
| 12 |
COPY requirements.txt .
|
| 13 |
RUN pip install --no-cache-dir -r requirements.txt
|
| 14 |
+
# Install Flash Attention 2 using pre-built wheels (requires torch to be installed first)
|
| 15 |
+
RUN pip install packaging
|
| 16 |
+
RUN pip install flash-attn --no-build-isolation --no-cache-dir
|
| 17 |
|
| 18 |
# Copy application code
|
| 19 |
COPY main.py .
|
config.json
CHANGED
|
@@ -40,6 +40,25 @@
|
|
| 40 |
"audio_token_id": 151648,
|
| 41 |
"dtype": "bfloat16",
|
| 42 |
"model_type": "vibevoice_asr",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
"semantic_tokenizer_encoder_config": {
|
| 44 |
"channels": 1,
|
| 45 |
"depths": [
|
|
@@ -130,5 +149,5 @@
|
|
| 130 |
"use_sliding_window": false,
|
| 131 |
"vocab_size": 152064
|
| 132 |
},
|
| 133 |
-
"transformers_version": "5.
|
| 134 |
}
|
|
|
|
| 40 |
"audio_token_id": 151648,
|
| 41 |
"dtype": "bfloat16",
|
| 42 |
"model_type": "vibevoice_asr",
|
| 43 |
+
"quantization_config": {
|
| 44 |
+
"include_input_output_embeddings": false,
|
| 45 |
+
"modules_to_not_convert": null,
|
| 46 |
+
"quant_method": "torchao",
|
| 47 |
+
"quant_type": {
|
| 48 |
+
"default": {
|
| 49 |
+
"_data": {
|
| 50 |
+
"set_inductor_config": true,
|
| 51 |
+
"weight_dtype": {
|
| 52 |
+
"_data": "float8_e4m3fn",
|
| 53 |
+
"_type": "torch.dtype"
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"_type": "Float8WeightOnlyConfig",
|
| 57 |
+
"_version": 2
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"untie_embedding_weights": false
|
| 61 |
+
},
|
| 62 |
"semantic_tokenizer_encoder_config": {
|
| 63 |
"channels": 1,
|
| 64 |
"depths": [
|
|
|
|
| 149 |
"use_sliding_window": false,
|
| 150 |
"vocab_size": 152064
|
| 151 |
},
|
| 152 |
+
"transformers_version": "5.9.0"
|
| 153 |
}
|
generation_config.json
CHANGED
|
@@ -7,6 +7,6 @@
|
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
"pad_token_id": 151655,
|
| 10 |
-
"transformers_version": "5.
|
| 11 |
"use_cache": true
|
| 12 |
}
|
|
|
|
| 7 |
"output_attentions": false,
|
| 8 |
"output_hidden_states": false,
|
| 9 |
"pad_token_id": 151655,
|
| 10 |
+
"transformers_version": "5.9.0",
|
| 11 |
"use_cache": true
|
| 12 |
}
|
main.py
CHANGED
|
@@ -7,6 +7,7 @@ import logging
|
|
| 7 |
import os
|
| 8 |
import sys
|
| 9 |
import tempfile
|
|
|
|
| 10 |
import traceback
|
| 11 |
|
| 12 |
from fastapi import FastAPI, Request, Response, HTTPException
|
|
@@ -14,6 +15,15 @@ from fastapi.responses import JSONResponse
|
|
| 14 |
|
| 15 |
from typing import Dict, Any
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
# this must come before attempts to import from transformers or torch
|
| 18 |
print(f'Versions: transformers: {version("transformers")}, torch: {version("torch")}')
|
| 19 |
|
|
@@ -24,10 +34,6 @@ import librosa
|
|
| 24 |
from transformers.models.auto.processing_auto import AutoProcessor
|
| 25 |
from transformers.models.vibevoice_asr.modeling_vibevoice_asr import VibeVoiceAsrForConditionalGeneration
|
| 26 |
|
| 27 |
-
# Configure logging
|
| 28 |
-
logging.basicConfig(level=logging.INFO)
|
| 29 |
-
logger = logging.getLogger(__name__)
|
| 30 |
-
|
| 31 |
class EndpointHandler():
|
| 32 |
def __init__(self, path=""):
|
| 33 |
# 1. Load the processor
|
|
@@ -37,13 +43,27 @@ class EndpointHandler():
|
|
| 37 |
self.model = VibeVoiceAsrForConditionalGeneration.from_pretrained(
|
| 38 |
path,
|
| 39 |
torch_dtype=torch.bfloat16,
|
| 40 |
-
device_map="auto"
|
|
|
|
| 41 |
)
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
# 3. Dynamically fetch the expected sample rate (usually 16kHz or 24kHz)
|
| 44 |
self.target_sr = getattr(self.processor.feature_extractor, "sampling_rate", 16000)
|
| 45 |
|
| 46 |
def __call__(self, data: Any) -> Dict[str, Any]:
|
|
|
|
| 47 |
# 1. Extract payload (Handles both JSON payloads and raw binary uploads)
|
| 48 |
if isinstance(data, dict):
|
| 49 |
data_copy = data.copy()
|
|
@@ -65,8 +85,11 @@ class EndpointHandler():
|
|
| 65 |
audio_array = None
|
| 66 |
|
| 67 |
# 2. Decode raw audio bytes (various formats) using librosa
|
|
|
|
|
|
|
| 68 |
try:
|
| 69 |
if isinstance(inputs, bytes):
|
|
|
|
| 70 |
# Raw bytes from binary upload (could be MP3, WAV, FLAC, etc.)
|
| 71 |
# Write to suffix-less temp file so librosa auto-detects format
|
| 72 |
temp_file = tempfile.NamedTemporaryFile("wb", delete=False)
|
|
@@ -78,6 +101,7 @@ class EndpointHandler():
|
|
| 78 |
|
| 79 |
elif isinstance(inputs, str):
|
| 80 |
if inputs.startswith("http://") or inputs.startswith("https://"):
|
|
|
|
| 81 |
# URL input - download first to be safe with librosa
|
| 82 |
import requests
|
| 83 |
response = requests.get(inputs)
|
|
@@ -88,6 +112,7 @@ class EndpointHandler():
|
|
| 88 |
|
| 89 |
audio_array, _ = librosa.load(temp_file.name, sr=self.target_sr, mono=True)
|
| 90 |
else:
|
|
|
|
| 91 |
# Try base64 decode
|
| 92 |
try:
|
| 93 |
decoded_bytes = base64.b64decode(inputs)
|
|
@@ -97,13 +122,23 @@ class EndpointHandler():
|
|
| 97 |
temp_file.close()
|
| 98 |
|
| 99 |
audio_array, _ = librosa.load(temp_file.name, sr=self.target_sr, mono=True)
|
| 100 |
-
except Exception:
|
|
|
|
| 101 |
# Fallback to assuming it's a local path
|
| 102 |
audio_array, _ = librosa.load(inputs, sr=self.target_sr, mono=True)
|
| 103 |
else:
|
|
|
|
| 104 |
# If already loaded (e.g. numpy array passed in some test environments)
|
| 105 |
audio_array = inputs
|
| 106 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
processed_inputs = self.processor.apply_transcription_request(
|
| 108 |
audio=audio_array,
|
| 109 |
prompt=hotwords
|
|
@@ -117,14 +152,19 @@ class EndpointHandler():
|
|
| 117 |
processed_inputs[k] = v.to(device=self.model.device, dtype=self.model.dtype)
|
| 118 |
else:
|
| 119 |
processed_inputs[k] = v.to(device=self.model.device)
|
|
|
|
| 120 |
|
| 121 |
# 4. Generate
|
|
|
|
|
|
|
| 122 |
with torch.no_grad():
|
| 123 |
output_ids = self.model.generate(
|
| 124 |
**processed_inputs,
|
| 125 |
# CRITICAL: VibeVoice needs a massive token limit to handle long-form audio.
|
| 126 |
max_new_tokens=32768
|
| 127 |
)
|
|
|
|
|
|
|
| 128 |
|
| 129 |
# Slice generated IDs to exclude the prompt (Fixes prompt leakage)
|
| 130 |
if "input_ids" in processed_inputs:
|
|
@@ -134,12 +174,18 @@ class EndpointHandler():
|
|
| 134 |
generated_ids = output_ids
|
| 135 |
|
| 136 |
# 5. Decode using return_format
|
|
|
|
|
|
|
| 137 |
try:
|
| 138 |
transcription = self.processor.decode(generated_ids, return_format=return_format)[0]
|
| 139 |
except Exception as e:
|
|
|
|
| 140 |
# Fallback to standard decode if return_format fails
|
| 141 |
transcription = self.processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
|
|
| 142 |
|
|
|
|
|
|
|
| 143 |
return {"result": transcription}
|
| 144 |
|
| 145 |
except Exception as e:
|
|
|
|
| 7 |
import os
|
| 8 |
import sys
|
| 9 |
import tempfile
|
| 10 |
+
import time
|
| 11 |
import traceback
|
| 12 |
|
| 13 |
from fastapi import FastAPI, Request, Response, HTTPException
|
|
|
|
| 15 |
|
| 16 |
from typing import Dict, Any
|
| 17 |
|
| 18 |
+
# Configure logging with timestamps as a fallback
|
| 19 |
+
logging.basicConfig(
|
| 20 |
+
level=logging.INFO,
|
| 21 |
+
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
| 22 |
+
datefmt="%Y-%m-%d %H:%M:%S"
|
| 23 |
+
)
|
| 24 |
+
# Use uvicorn's error logger if running under uvicorn, which handles formatting nicely
|
| 25 |
+
logger = logging.getLogger("uvicorn.error")
|
| 26 |
+
|
| 27 |
# this must come before attempts to import from transformers or torch
|
| 28 |
print(f'Versions: transformers: {version("transformers")}, torch: {version("torch")}')
|
| 29 |
|
|
|
|
| 34 |
from transformers.models.auto.processing_auto import AutoProcessor
|
| 35 |
from transformers.models.vibevoice_asr.modeling_vibevoice_asr import VibeVoiceAsrForConditionalGeneration
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
class EndpointHandler():
|
| 38 |
def __init__(self, path=""):
|
| 39 |
# 1. Load the processor
|
|
|
|
| 43 |
self.model = VibeVoiceAsrForConditionalGeneration.from_pretrained(
|
| 44 |
path,
|
| 45 |
torch_dtype=torch.bfloat16,
|
| 46 |
+
device_map="auto",
|
| 47 |
+
attn_implementation="flash_attention_2"
|
| 48 |
)
|
| 49 |
|
| 50 |
+
# Print layer device allocation
|
| 51 |
+
if hasattr(self.model, "hf_device_map"):
|
| 52 |
+
logger.info("Model layers device allocation (hf_device_map):")
|
| 53 |
+
for layer_name, device in self.model.hf_device_map.items():
|
| 54 |
+
logger.info(f" - {layer_name}: {device}")
|
| 55 |
+
else:
|
| 56 |
+
# Fallback if hf_device_map is not populated
|
| 57 |
+
devices = set()
|
| 58 |
+
for name, param in self.model.named_parameters():
|
| 59 |
+
devices.add(str(param.device))
|
| 60 |
+
logger.info(f"Model loaded. Active devices for parameters: {list(devices)}")
|
| 61 |
+
|
| 62 |
# 3. Dynamically fetch the expected sample rate (usually 16kHz or 24kHz)
|
| 63 |
self.target_sr = getattr(self.processor.feature_extractor, "sampling_rate", 16000)
|
| 64 |
|
| 65 |
def __call__(self, data: Any) -> Dict[str, Any]:
|
| 66 |
+
start_time = time.time()
|
| 67 |
# 1. Extract payload (Handles both JSON payloads and raw binary uploads)
|
| 68 |
if isinstance(data, dict):
|
| 69 |
data_copy = data.copy()
|
|
|
|
| 85 |
audio_array = None
|
| 86 |
|
| 87 |
# 2. Decode raw audio bytes (various formats) using librosa
|
| 88 |
+
logger.info("Starting audio loading and preprocessing...")
|
| 89 |
+
audio_load_start = time.time()
|
| 90 |
try:
|
| 91 |
if isinstance(inputs, bytes):
|
| 92 |
+
logger.info(f"Decoding audio from raw bytes ({len(inputs)} bytes)...")
|
| 93 |
# Raw bytes from binary upload (could be MP3, WAV, FLAC, etc.)
|
| 94 |
# Write to suffix-less temp file so librosa auto-detects format
|
| 95 |
temp_file = tempfile.NamedTemporaryFile("wb", delete=False)
|
|
|
|
| 101 |
|
| 102 |
elif isinstance(inputs, str):
|
| 103 |
if inputs.startswith("http://") or inputs.startswith("https://"):
|
| 104 |
+
logger.info(f"Downloading audio from URL: {inputs}...")
|
| 105 |
# URL input - download first to be safe with librosa
|
| 106 |
import requests
|
| 107 |
response = requests.get(inputs)
|
|
|
|
| 112 |
|
| 113 |
audio_array, _ = librosa.load(temp_file.name, sr=self.target_sr, mono=True)
|
| 114 |
else:
|
| 115 |
+
logger.info("Decoding audio from Base64 string...")
|
| 116 |
# Try base64 decode
|
| 117 |
try:
|
| 118 |
decoded_bytes = base64.b64decode(inputs)
|
|
|
|
| 122 |
temp_file.close()
|
| 123 |
|
| 124 |
audio_array, _ = librosa.load(temp_file.name, sr=self.target_sr, mono=True)
|
| 125 |
+
except Exception as e:
|
| 126 |
+
logger.info(f"Base64 decode failed ({e}), assuming input is a local file path...")
|
| 127 |
# Fallback to assuming it's a local path
|
| 128 |
audio_array, _ = librosa.load(inputs, sr=self.target_sr, mono=True)
|
| 129 |
else:
|
| 130 |
+
logger.info("Using pre-loaded audio array...")
|
| 131 |
# If already loaded (e.g. numpy array passed in some test environments)
|
| 132 |
audio_array = inputs
|
| 133 |
|
| 134 |
+
audio_load_duration = time.time() - audio_load_start
|
| 135 |
+
audio_duration_sec = len(audio_array) / self.target_sr if audio_array is not None else 0
|
| 136 |
+
logger.info(f"Audio loaded successfully in {audio_load_duration:.3f}s. "
|
| 137 |
+
f"Audio duration: {audio_duration_sec:.2f}s, Sample Rate: {self.target_sr}Hz")
|
| 138 |
+
|
| 139 |
+
# 3. Prepare inputs using the recommended API
|
| 140 |
+
logger.info("Preprocessing audio features...")
|
| 141 |
+
preprocess_start = time.time()
|
| 142 |
processed_inputs = self.processor.apply_transcription_request(
|
| 143 |
audio=audio_array,
|
| 144 |
prompt=hotwords
|
|
|
|
| 152 |
processed_inputs[k] = v.to(device=self.model.device, dtype=self.model.dtype)
|
| 153 |
else:
|
| 154 |
processed_inputs[k] = v.to(device=self.model.device)
|
| 155 |
+
logger.info(f"Preprocessing completed in {time.time() - preprocess_start:.3f}s.")
|
| 156 |
|
| 157 |
# 4. Generate
|
| 158 |
+
logger.info("Starting model inference (generation)...")
|
| 159 |
+
inference_start = time.time()
|
| 160 |
with torch.no_grad():
|
| 161 |
output_ids = self.model.generate(
|
| 162 |
**processed_inputs,
|
| 163 |
# CRITICAL: VibeVoice needs a massive token limit to handle long-form audio.
|
| 164 |
max_new_tokens=32768
|
| 165 |
)
|
| 166 |
+
inference_duration = time.time() - inference_start
|
| 167 |
+
logger.info(f"Model inference completed in {inference_duration:.3f}s.")
|
| 168 |
|
| 169 |
# Slice generated IDs to exclude the prompt (Fixes prompt leakage)
|
| 170 |
if "input_ids" in processed_inputs:
|
|
|
|
| 174 |
generated_ids = output_ids
|
| 175 |
|
| 176 |
# 5. Decode using return_format
|
| 177 |
+
logger.info(f"Decoding generated tokens to text (format: '{return_format}')...")
|
| 178 |
+
decode_start = time.time()
|
| 179 |
try:
|
| 180 |
transcription = self.processor.decode(generated_ids, return_format=return_format)[0]
|
| 181 |
except Exception as e:
|
| 182 |
+
logger.warning(f"Decoding with return_format='{return_format}' failed, falling back to batch_decode. Error: {e}")
|
| 183 |
# Fallback to standard decode if return_format fails
|
| 184 |
transcription = self.processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
| 185 |
+
logger.info(f"Token decoding completed in {time.time() - decode_start:.3f}s.")
|
| 186 |
|
| 187 |
+
total_duration = time.time() - start_time
|
| 188 |
+
logger.info(f"Request processed successfully in {total_duration:.3f}s.")
|
| 189 |
return {"result": transcription}
|
| 190 |
|
| 191 |
except Exception as e:
|
model-00002-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:65e419d28fc8c87d6938ec611c7b425b38e391c80a2df59c2b4935f6fd65c7c2
|
| 3 |
-
size 2389316008
|
|
|
|
|
|
|
|
|
|
|
|
model-00003-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:30f574c764550d26c654cc3f5dd000b90b0c3305db955267c577001c1013fdf7
|
| 3 |
-
size 2466376400
|
|
|
|
|
|
|
|
|
|
|
|
model-00004-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8fa3d9350f0a8cc97524617ff582e451159bfdba2ef0b2e372a627518ef681b1
|
| 3 |
-
size 2466376432
|
|
|
|
|
|
|
|
|
|
|
|
model-00005-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:5015ecacc86d897d20d5e42ba52ef83355d42f587d3b158ff897ec94847bd083
|
| 3 |
-
size 2499431160
|
|
|
|
|
|
|
|
|
|
|
|
model-00006-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:7463d75607185c118925cea6a60a5698aaa6f428e626bcee774572bdc28ef55d
|
| 3 |
-
size 1831435704
|
|
|
|
|
|
|
|
|
|
|
|
model-00007-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b52aa2fab9640bcac5201a278f540b018c439ed4e99516d9ff30ea1ae399525e
|
| 3 |
-
size 2482226384
|
|
|
|
|
|
|
|
|
|
|
|
model-00008-of-00008.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:a66ced85b619507e1970dc51be45786ff55803ccc63658765e412ea23d9a8ace
|
| 3 |
-
size 37262376
|
|
|
|
|
|
|
|
|
|
|
|
model-00001-of-00008.safetensors → model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5e993e59216ef2ba3213a5cec6d76594f0ed9205d168352c037f31b5b6e45e9
|
| 3 |
+
size 9511924456
|
model.safetensors.index.json
DELETED
|
@@ -1,909 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_parameters": 8330325888,
|
| 4 |
-
"total_size": 16660651776
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"acoustic_tokenizer_encoder.conv_layers.0.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 8 |
-
"acoustic_tokenizer_encoder.conv_layers.0.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 9 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 10 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 11 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 12 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 13 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 14 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 15 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 16 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 17 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 18 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 19 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 20 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 21 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 22 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 23 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 24 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 25 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 26 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 27 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 28 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 29 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 30 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 31 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 32 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 33 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 34 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 35 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 36 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 37 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 38 |
-
"acoustic_tokenizer_encoder.conv_layers.0.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 39 |
-
"acoustic_tokenizer_encoder.conv_layers.1.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 40 |
-
"acoustic_tokenizer_encoder.conv_layers.1.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 41 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 42 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 43 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 44 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 45 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 46 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 47 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 48 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 49 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 50 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 51 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 52 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 53 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 54 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 55 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 56 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 57 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 58 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 59 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 60 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 61 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 62 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 63 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 64 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 65 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 66 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 67 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 68 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 69 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 70 |
-
"acoustic_tokenizer_encoder.conv_layers.1.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 71 |
-
"acoustic_tokenizer_encoder.conv_layers.2.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 72 |
-
"acoustic_tokenizer_encoder.conv_layers.2.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 73 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 74 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 75 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 76 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 77 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 78 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 79 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 80 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 81 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 82 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 83 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 84 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 85 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 86 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 87 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 88 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 89 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 90 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 91 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 92 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 93 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 94 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 95 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 96 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 97 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 98 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 99 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 100 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 101 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 102 |
-
"acoustic_tokenizer_encoder.conv_layers.2.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 103 |
-
"acoustic_tokenizer_encoder.conv_layers.3.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 104 |
-
"acoustic_tokenizer_encoder.conv_layers.3.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 105 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 106 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 107 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 108 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 109 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 110 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 111 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 112 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 113 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 114 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 115 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 116 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 117 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 118 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 119 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 120 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 121 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 122 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 123 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 124 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 125 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 126 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 127 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 128 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 129 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 130 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 131 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 132 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 133 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 134 |
-
"acoustic_tokenizer_encoder.conv_layers.3.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 135 |
-
"acoustic_tokenizer_encoder.conv_layers.4.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 136 |
-
"acoustic_tokenizer_encoder.conv_layers.4.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 137 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 138 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 139 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 140 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 141 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 142 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 143 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 144 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 145 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 146 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 147 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 148 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 149 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 150 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 151 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 152 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 153 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 154 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 155 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 156 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 157 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 158 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 159 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 160 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 161 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 162 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 163 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 164 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 165 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 166 |
-
"acoustic_tokenizer_encoder.conv_layers.4.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 167 |
-
"acoustic_tokenizer_encoder.conv_layers.5.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 168 |
-
"acoustic_tokenizer_encoder.conv_layers.5.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 169 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 170 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 171 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 172 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 173 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 174 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 175 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 176 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 177 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 178 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 179 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 180 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 181 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 182 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 183 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 184 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 185 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 186 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 187 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 188 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 189 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 190 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 191 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 192 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 193 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 194 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 195 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 196 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 197 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 198 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 199 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 200 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 201 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 202 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 203 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 204 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 205 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.gamma": "model-00007-of-00008.safetensors",
|
| 206 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 207 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 208 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.3.norm.weight": "model-00007-of-00008.safetensors",
|
| 209 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 210 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 211 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 212 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 213 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 214 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 215 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.gamma": "model-00007-of-00008.safetensors",
|
| 216 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 217 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 218 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.4.norm.weight": "model-00007-of-00008.safetensors",
|
| 219 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 220 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 221 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 222 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 223 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 224 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 225 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.gamma": "model-00007-of-00008.safetensors",
|
| 226 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 227 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 228 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.5.norm.weight": "model-00007-of-00008.safetensors",
|
| 229 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 230 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 231 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 232 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 233 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 234 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 235 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.gamma": "model-00007-of-00008.safetensors",
|
| 236 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 237 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 238 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.6.norm.weight": "model-00007-of-00008.safetensors",
|
| 239 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 240 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 241 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 242 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 243 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 244 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 245 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.gamma": "model-00007-of-00008.safetensors",
|
| 246 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 247 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 248 |
-
"acoustic_tokenizer_encoder.conv_layers.5.stage.7.norm.weight": "model-00007-of-00008.safetensors",
|
| 249 |
-
"acoustic_tokenizer_encoder.head.conv.bias": "model-00007-of-00008.safetensors",
|
| 250 |
-
"acoustic_tokenizer_encoder.head.conv.weight": "model-00007-of-00008.safetensors",
|
| 251 |
-
"acoustic_tokenizer_encoder.stem.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 252 |
-
"acoustic_tokenizer_encoder.stem.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 253 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 254 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 255 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 256 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 257 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 258 |
-
"acoustic_tokenizer_encoder.stem.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 259 |
-
"acoustic_tokenizer_encoder.stem.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 260 |
-
"acoustic_tokenizer_encoder.stem.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 261 |
-
"acoustic_tokenizer_encoder.stem.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 262 |
-
"acoustic_tokenizer_encoder.stem.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 263 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 264 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 265 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 266 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 267 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 268 |
-
"acoustic_tokenizer_encoder.stem.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 269 |
-
"acoustic_tokenizer_encoder.stem.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 270 |
-
"acoustic_tokenizer_encoder.stem.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 271 |
-
"acoustic_tokenizer_encoder.stem.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 272 |
-
"acoustic_tokenizer_encoder.stem.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 273 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 274 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 275 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 276 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 277 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 278 |
-
"acoustic_tokenizer_encoder.stem.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 279 |
-
"acoustic_tokenizer_encoder.stem.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 280 |
-
"acoustic_tokenizer_encoder.stem.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 281 |
-
"acoustic_tokenizer_encoder.stem.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 282 |
-
"acoustic_tokenizer_encoder.stem.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 283 |
-
"language_model.lm_head.weight": "model-00007-of-00008.safetensors",
|
| 284 |
-
"language_model.model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
| 285 |
-
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 286 |
-
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 287 |
-
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 288 |
-
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 289 |
-
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 290 |
-
"language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 291 |
-
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 292 |
-
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 293 |
-
"language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 294 |
-
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 295 |
-
"language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 296 |
-
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 297 |
-
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 298 |
-
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 299 |
-
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 300 |
-
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 301 |
-
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 302 |
-
"language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 303 |
-
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 304 |
-
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 305 |
-
"language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 306 |
-
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 307 |
-
"language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 308 |
-
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 309 |
-
"language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 310 |
-
"language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 311 |
-
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 312 |
-
"language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 313 |
-
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 314 |
-
"language_model.model.layers.10.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 315 |
-
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 316 |
-
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 317 |
-
"language_model.model.layers.10.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 318 |
-
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 319 |
-
"language_model.model.layers.10.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 320 |
-
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 321 |
-
"language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 322 |
-
"language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 323 |
-
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 324 |
-
"language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 325 |
-
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 326 |
-
"language_model.model.layers.11.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 327 |
-
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 328 |
-
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 329 |
-
"language_model.model.layers.11.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 330 |
-
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 331 |
-
"language_model.model.layers.11.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 332 |
-
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 333 |
-
"language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 334 |
-
"language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 335 |
-
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 336 |
-
"language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 337 |
-
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 338 |
-
"language_model.model.layers.12.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 339 |
-
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 340 |
-
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 341 |
-
"language_model.model.layers.12.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 342 |
-
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 343 |
-
"language_model.model.layers.12.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 344 |
-
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 345 |
-
"language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 346 |
-
"language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 347 |
-
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 348 |
-
"language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 349 |
-
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 350 |
-
"language_model.model.layers.13.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 351 |
-
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 352 |
-
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 353 |
-
"language_model.model.layers.13.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 354 |
-
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 355 |
-
"language_model.model.layers.13.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 356 |
-
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 357 |
-
"language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 358 |
-
"language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 359 |
-
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 360 |
-
"language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 361 |
-
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 362 |
-
"language_model.model.layers.14.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 363 |
-
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 364 |
-
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 365 |
-
"language_model.model.layers.14.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 366 |
-
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 367 |
-
"language_model.model.layers.14.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 368 |
-
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 369 |
-
"language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 370 |
-
"language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 371 |
-
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 372 |
-
"language_model.model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 373 |
-
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 374 |
-
"language_model.model.layers.15.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 375 |
-
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 376 |
-
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 377 |
-
"language_model.model.layers.15.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 378 |
-
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 379 |
-
"language_model.model.layers.15.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 380 |
-
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 381 |
-
"language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 382 |
-
"language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 383 |
-
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 384 |
-
"language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 385 |
-
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 386 |
-
"language_model.model.layers.16.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 387 |
-
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 388 |
-
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 389 |
-
"language_model.model.layers.16.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 390 |
-
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 391 |
-
"language_model.model.layers.16.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 392 |
-
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 393 |
-
"language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 394 |
-
"language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
| 395 |
-
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 396 |
-
"language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 397 |
-
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 398 |
-
"language_model.model.layers.17.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 399 |
-
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 400 |
-
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 401 |
-
"language_model.model.layers.17.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 402 |
-
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 403 |
-
"language_model.model.layers.17.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 404 |
-
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 405 |
-
"language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 406 |
-
"language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 407 |
-
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
| 408 |
-
"language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
| 409 |
-
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 410 |
-
"language_model.model.layers.18.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 411 |
-
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 412 |
-
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 413 |
-
"language_model.model.layers.18.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 414 |
-
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 415 |
-
"language_model.model.layers.18.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 416 |
-
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 417 |
-
"language_model.model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 418 |
-
"language_model.model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 419 |
-
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 420 |
-
"language_model.model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 421 |
-
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 422 |
-
"language_model.model.layers.19.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 423 |
-
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 424 |
-
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 425 |
-
"language_model.model.layers.19.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 426 |
-
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 427 |
-
"language_model.model.layers.19.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 428 |
-
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 429 |
-
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 430 |
-
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
| 431 |
-
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
| 432 |
-
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
| 433 |
-
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 434 |
-
"language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 435 |
-
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 436 |
-
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 437 |
-
"language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 438 |
-
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 439 |
-
"language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 440 |
-
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 441 |
-
"language_model.model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 442 |
-
"language_model.model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 443 |
-
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 444 |
-
"language_model.model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 445 |
-
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 446 |
-
"language_model.model.layers.20.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 447 |
-
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 448 |
-
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 449 |
-
"language_model.model.layers.20.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 450 |
-
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 451 |
-
"language_model.model.layers.20.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 452 |
-
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 453 |
-
"language_model.model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 454 |
-
"language_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 455 |
-
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 456 |
-
"language_model.model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 457 |
-
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 458 |
-
"language_model.model.layers.21.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 459 |
-
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 460 |
-
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 461 |
-
"language_model.model.layers.21.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 462 |
-
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 463 |
-
"language_model.model.layers.21.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 464 |
-
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 465 |
-
"language_model.model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 466 |
-
"language_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 467 |
-
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 468 |
-
"language_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 469 |
-
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 470 |
-
"language_model.model.layers.22.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 471 |
-
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 472 |
-
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 473 |
-
"language_model.model.layers.22.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 474 |
-
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 475 |
-
"language_model.model.layers.22.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 476 |
-
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 477 |
-
"language_model.model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 478 |
-
"language_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
| 479 |
-
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
| 480 |
-
"language_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
| 481 |
-
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 482 |
-
"language_model.model.layers.23.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 483 |
-
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 484 |
-
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 485 |
-
"language_model.model.layers.23.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 486 |
-
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 487 |
-
"language_model.model.layers.23.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 488 |
-
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 489 |
-
"language_model.model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 490 |
-
"language_model.model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 491 |
-
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 492 |
-
"language_model.model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 493 |
-
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 494 |
-
"language_model.model.layers.24.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 495 |
-
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 496 |
-
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 497 |
-
"language_model.model.layers.24.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 498 |
-
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 499 |
-
"language_model.model.layers.24.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 500 |
-
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 501 |
-
"language_model.model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 502 |
-
"language_model.model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 503 |
-
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 504 |
-
"language_model.model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 505 |
-
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 506 |
-
"language_model.model.layers.25.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 507 |
-
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 508 |
-
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 509 |
-
"language_model.model.layers.25.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 510 |
-
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 511 |
-
"language_model.model.layers.25.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 512 |
-
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 513 |
-
"language_model.model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 514 |
-
"language_model.model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 515 |
-
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 516 |
-
"language_model.model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 517 |
-
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 518 |
-
"language_model.model.layers.26.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 519 |
-
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 520 |
-
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 521 |
-
"language_model.model.layers.26.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 522 |
-
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 523 |
-
"language_model.model.layers.26.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 524 |
-
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 525 |
-
"language_model.model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 526 |
-
"language_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
| 527 |
-
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
| 528 |
-
"language_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
| 529 |
-
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 530 |
-
"language_model.model.layers.27.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 531 |
-
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 532 |
-
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 533 |
-
"language_model.model.layers.27.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 534 |
-
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 535 |
-
"language_model.model.layers.27.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 536 |
-
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 537 |
-
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 538 |
-
"language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 539 |
-
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 540 |
-
"language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 541 |
-
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 542 |
-
"language_model.model.layers.3.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 543 |
-
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 544 |
-
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 545 |
-
"language_model.model.layers.3.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 546 |
-
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 547 |
-
"language_model.model.layers.3.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 548 |
-
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 549 |
-
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 550 |
-
"language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 551 |
-
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 552 |
-
"language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 553 |
-
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 554 |
-
"language_model.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 555 |
-
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 556 |
-
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 557 |
-
"language_model.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 558 |
-
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 559 |
-
"language_model.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 560 |
-
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 561 |
-
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 562 |
-
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 563 |
-
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 564 |
-
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 565 |
-
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 566 |
-
"language_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 567 |
-
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 568 |
-
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 569 |
-
"language_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 570 |
-
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 571 |
-
"language_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 572 |
-
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 573 |
-
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 574 |
-
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 575 |
-
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 576 |
-
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 577 |
-
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 578 |
-
"language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 579 |
-
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 580 |
-
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 581 |
-
"language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 582 |
-
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 583 |
-
"language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 584 |
-
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 585 |
-
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 586 |
-
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
| 587 |
-
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
| 588 |
-
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
| 589 |
-
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 590 |
-
"language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 591 |
-
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 592 |
-
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 593 |
-
"language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 594 |
-
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 595 |
-
"language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 596 |
-
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 597 |
-
"language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 598 |
-
"language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 599 |
-
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 600 |
-
"language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 601 |
-
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 602 |
-
"language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 603 |
-
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 604 |
-
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 605 |
-
"language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 606 |
-
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 607 |
-
"language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 608 |
-
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 609 |
-
"language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 610 |
-
"language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
| 611 |
-
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
| 612 |
-
"language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
| 613 |
-
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 614 |
-
"language_model.model.layers.9.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 615 |
-
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 616 |
-
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 617 |
-
"language_model.model.layers.9.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 618 |
-
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 619 |
-
"language_model.model.layers.9.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 620 |
-
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 621 |
-
"language_model.model.norm.weight": "model-00006-of-00008.safetensors",
|
| 622 |
-
"multi_modal_projector.acoustic_linear_1.bias": "model-00007-of-00008.safetensors",
|
| 623 |
-
"multi_modal_projector.acoustic_linear_1.weight": "model-00007-of-00008.safetensors",
|
| 624 |
-
"multi_modal_projector.acoustic_linear_2.bias": "model-00007-of-00008.safetensors",
|
| 625 |
-
"multi_modal_projector.acoustic_linear_2.weight": "model-00007-of-00008.safetensors",
|
| 626 |
-
"multi_modal_projector.acoustic_norm.weight": "model-00007-of-00008.safetensors",
|
| 627 |
-
"multi_modal_projector.semantic_linear_1.bias": "model-00007-of-00008.safetensors",
|
| 628 |
-
"multi_modal_projector.semantic_linear_1.weight": "model-00007-of-00008.safetensors",
|
| 629 |
-
"multi_modal_projector.semantic_linear_2.bias": "model-00007-of-00008.safetensors",
|
| 630 |
-
"multi_modal_projector.semantic_linear_2.weight": "model-00007-of-00008.safetensors",
|
| 631 |
-
"multi_modal_projector.semantic_norm.weight": "model-00007-of-00008.safetensors",
|
| 632 |
-
"semantic_tokenizer_encoder.conv_layers.0.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 633 |
-
"semantic_tokenizer_encoder.conv_layers.0.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 634 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 635 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 636 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 637 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 638 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 639 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 640 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 641 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 642 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 643 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 644 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 645 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 646 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 647 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 648 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 649 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 650 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 651 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 652 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 653 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 654 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 655 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 656 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 657 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 658 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 659 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 660 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 661 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 662 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 663 |
-
"semantic_tokenizer_encoder.conv_layers.0.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 664 |
-
"semantic_tokenizer_encoder.conv_layers.1.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 665 |
-
"semantic_tokenizer_encoder.conv_layers.1.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 666 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 667 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 668 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 669 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 670 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 671 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 672 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 673 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 674 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 675 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 676 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 677 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 678 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 679 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 680 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 681 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 682 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 683 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 684 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 685 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 686 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 687 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 688 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 689 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 690 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 691 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 692 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 693 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 694 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 695 |
-
"semantic_tokenizer_encoder.conv_layers.1.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 696 |
-
"semantic_tokenizer_encoder.conv_layers.2.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 697 |
-
"semantic_tokenizer_encoder.conv_layers.2.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 698 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 699 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 700 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 701 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 702 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 703 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 704 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 705 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 706 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 707 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 708 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 709 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 710 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 711 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 712 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 713 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 714 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 715 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 716 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 717 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 718 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 719 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 720 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 721 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 722 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 723 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 724 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 725 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 726 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 727 |
-
"semantic_tokenizer_encoder.conv_layers.2.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 728 |
-
"semantic_tokenizer_encoder.conv_layers.3.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 729 |
-
"semantic_tokenizer_encoder.conv_layers.3.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 730 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 731 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 732 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 733 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 734 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 735 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 736 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 737 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 738 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 739 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 740 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 741 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 742 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 743 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 744 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 745 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 746 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 747 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 748 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 749 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 750 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 751 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 752 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 753 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 754 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 755 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 756 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 757 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 758 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 759 |
-
"semantic_tokenizer_encoder.conv_layers.3.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 760 |
-
"semantic_tokenizer_encoder.conv_layers.4.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 761 |
-
"semantic_tokenizer_encoder.conv_layers.4.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 762 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 763 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 764 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 765 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 766 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 767 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 768 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 769 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 770 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 771 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 772 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 773 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 774 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 775 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 776 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 777 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 778 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 779 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 780 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 781 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 782 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 783 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 784 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 785 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 786 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 787 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 788 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 789 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 790 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 791 |
-
"semantic_tokenizer_encoder.conv_layers.4.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 792 |
-
"semantic_tokenizer_encoder.conv_layers.5.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 793 |
-
"semantic_tokenizer_encoder.conv_layers.5.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 794 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 795 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 796 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 797 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 798 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 799 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 800 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 801 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 802 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 803 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 804 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 805 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 806 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 807 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 808 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 809 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 810 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 811 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 812 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 813 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 814 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 815 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 816 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 817 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 818 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 819 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 820 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 821 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 822 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 823 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.2.norm.weight": "model-00007-of-00008.safetensors",
|
| 824 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 825 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 826 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 827 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 828 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 829 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 830 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.gamma": "model-00007-of-00008.safetensors",
|
| 831 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 832 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 833 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.3.norm.weight": "model-00007-of-00008.safetensors",
|
| 834 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 835 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 836 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 837 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 838 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 839 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 840 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.gamma": "model-00007-of-00008.safetensors",
|
| 841 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 842 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 843 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.4.norm.weight": "model-00007-of-00008.safetensors",
|
| 844 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 845 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 846 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 847 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 848 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 849 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 850 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.gamma": "model-00007-of-00008.safetensors",
|
| 851 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 852 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 853 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.5.norm.weight": "model-00007-of-00008.safetensors",
|
| 854 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 855 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 856 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 857 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 858 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 859 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 860 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.gamma": "model-00007-of-00008.safetensors",
|
| 861 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 862 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 863 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.6.norm.weight": "model-00007-of-00008.safetensors",
|
| 864 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 865 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 866 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear2.bias": "model-00008-of-00008.safetensors",
|
| 867 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn.linear2.weight": "model-00008-of-00008.safetensors",
|
| 868 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 869 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 870 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.gamma": "model-00007-of-00008.safetensors",
|
| 871 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.mixer.conv.bias": "model-00008-of-00008.safetensors",
|
| 872 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.mixer.conv.weight": "model-00008-of-00008.safetensors",
|
| 873 |
-
"semantic_tokenizer_encoder.conv_layers.5.stage.7.norm.weight": "model-00007-of-00008.safetensors",
|
| 874 |
-
"semantic_tokenizer_encoder.head.conv.bias": "model-00008-of-00008.safetensors",
|
| 875 |
-
"semantic_tokenizer_encoder.head.conv.weight": "model-00008-of-00008.safetensors",
|
| 876 |
-
"semantic_tokenizer_encoder.stem.conv.conv.bias": "model-00007-of-00008.safetensors",
|
| 877 |
-
"semantic_tokenizer_encoder.stem.conv.conv.weight": "model-00007-of-00008.safetensors",
|
| 878 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 879 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 880 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 881 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 882 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 883 |
-
"semantic_tokenizer_encoder.stem.stage.0.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 884 |
-
"semantic_tokenizer_encoder.stem.stage.0.gamma": "model-00007-of-00008.safetensors",
|
| 885 |
-
"semantic_tokenizer_encoder.stem.stage.0.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 886 |
-
"semantic_tokenizer_encoder.stem.stage.0.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 887 |
-
"semantic_tokenizer_encoder.stem.stage.0.norm.weight": "model-00007-of-00008.safetensors",
|
| 888 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 889 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 890 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 891 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 892 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 893 |
-
"semantic_tokenizer_encoder.stem.stage.1.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 894 |
-
"semantic_tokenizer_encoder.stem.stage.1.gamma": "model-00007-of-00008.safetensors",
|
| 895 |
-
"semantic_tokenizer_encoder.stem.stage.1.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 896 |
-
"semantic_tokenizer_encoder.stem.stage.1.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 897 |
-
"semantic_tokenizer_encoder.stem.stage.1.norm.weight": "model-00007-of-00008.safetensors",
|
| 898 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn.linear1.bias": "model-00007-of-00008.safetensors",
|
| 899 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn.linear1.weight": "model-00007-of-00008.safetensors",
|
| 900 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn.linear2.bias": "model-00007-of-00008.safetensors",
|
| 901 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn.linear2.weight": "model-00007-of-00008.safetensors",
|
| 902 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn_gamma": "model-00007-of-00008.safetensors",
|
| 903 |
-
"semantic_tokenizer_encoder.stem.stage.2.ffn_norm.weight": "model-00007-of-00008.safetensors",
|
| 904 |
-
"semantic_tokenizer_encoder.stem.stage.2.gamma": "model-00007-of-00008.safetensors",
|
| 905 |
-
"semantic_tokenizer_encoder.stem.stage.2.mixer.conv.bias": "model-00007-of-00008.safetensors",
|
| 906 |
-
"semantic_tokenizer_encoder.stem.stage.2.mixer.conv.weight": "model-00007-of-00008.safetensors",
|
| 907 |
-
"semantic_tokenizer_encoder.stem.stage.2.norm.weight": "model-00007-of-00008.safetensors"
|
| 908 |
-
}
|
| 909 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
quantize.py
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
import argparse
|
| 3 |
+
import os
|
| 4 |
+
import sys
|
| 5 |
+
import logging
|
| 6 |
+
import torch
|
| 7 |
+
from transformers import AutoProcessor, BitsAndBytesConfig, TorchAoConfig
|
| 8 |
+
|
| 9 |
+
# We need to bypass lazy-loader for VibeVoice classes as in main.py
|
| 10 |
+
try:
|
| 11 |
+
from transformers.models.vibevoice_asr.modeling_vibevoice_asr import VibeVoiceAsrForConditionalGeneration
|
| 12 |
+
except ImportError as e:
|
| 13 |
+
print(f"Error importing VibeVoice modeling: {e}", file=sys.stderr)
|
| 14 |
+
print("Please ensure the correct transformers version is installed.", file=sys.stderr)
|
| 15 |
+
sys.exit(1)
|
| 16 |
+
|
| 17 |
+
logging.basicConfig(
|
| 18 |
+
level=logging.INFO,
|
| 19 |
+
format="%(asctime)s [%(levelname)s] %(message)s",
|
| 20 |
+
datefmt="%Y-%m-%d %H:%M:%S"
|
| 21 |
+
)
|
| 22 |
+
logger = logging.getLogger(__name__)
|
| 23 |
+
|
| 24 |
+
def main():
|
| 25 |
+
parser = argparse.ArgumentParser(description="Quantize VibeVoice ASR model and save the serialized weights.")
|
| 26 |
+
parser.add_argument("--model_dir", type=str, default=os.environ.get("MODEL_DIR", "./repository"),
|
| 27 |
+
help="Path to the original unquantized model directory (default: ./repository or $MODEL_DIR)")
|
| 28 |
+
parser.add_argument("--output_dir", type=str, required=True,
|
| 29 |
+
help="Path where the quantized model should be saved (must be a new/empty directory)")
|
| 30 |
+
parser.add_argument("--format", type=str, choices=["int8", "int4", "fp8"], default="int8",
|
| 31 |
+
help="Quantization format (int8, int4, or fp8, default: int8)")
|
| 32 |
+
|
| 33 |
+
args = parser.parse_args()
|
| 34 |
+
|
| 35 |
+
if not os.path.exists(args.model_dir):
|
| 36 |
+
logger.error(f"Source model directory does not exist: {args.model_dir}")
|
| 37 |
+
sys.exit(1)
|
| 38 |
+
|
| 39 |
+
# Clean path resolution
|
| 40 |
+
args.model_dir = os.path.abspath(args.model_dir)
|
| 41 |
+
args.output_dir = os.path.abspath(args.output_dir)
|
| 42 |
+
|
| 43 |
+
if os.path.exists(args.output_dir) and os.path.exists(os.path.join(args.output_dir, "config.json")):
|
| 44 |
+
logger.warning(f"Output directory '{args.output_dir}' already contains a model config. "
|
| 45 |
+
f"Saving here will overwrite it and may leave orphan weight files.")
|
| 46 |
+
confirm = input("Do you want to proceed anyway? (y/N): ")
|
| 47 |
+
if confirm.lower() != 'y':
|
| 48 |
+
logger.info("Aborted by user.")
|
| 49 |
+
sys.exit(0)
|
| 50 |
+
|
| 51 |
+
# Configure quantization
|
| 52 |
+
if args.format == "int8":
|
| 53 |
+
logger.info("Configuring 8-bit Integer (BitsAndBytes) quantization...")
|
| 54 |
+
quantization_config = BitsAndBytesConfig(load_in_8bit=True)
|
| 55 |
+
elif args.format == "int4":
|
| 56 |
+
logger.info("Configuring 4-bit (NF4 BitsAndBytes) quantization...")
|
| 57 |
+
quantization_config = BitsAndBytesConfig(
|
| 58 |
+
load_in_4bit=True,
|
| 59 |
+
bnb_4bit_compute_dtype=torch.bfloat16,
|
| 60 |
+
bnb_4bit_use_double_quant=True,
|
| 61 |
+
bnb_4bit_quant_type="nf4"
|
| 62 |
+
)
|
| 63 |
+
elif args.format == "fp8":
|
| 64 |
+
logger.info("Configuring 8-bit Floating Point (TorchAO Float8 Weight-Only) quantization...")
|
| 65 |
+
try:
|
| 66 |
+
from torchao.quantization import Float8WeightOnlyConfig
|
| 67 |
+
except ImportError:
|
| 68 |
+
logger.error("torchao is not installed. Please run 'pip install torchao' to use FP8 quantization.")
|
| 69 |
+
sys.exit(1)
|
| 70 |
+
quantization_config = TorchAoConfig(Float8WeightOnlyConfig())
|
| 71 |
+
|
| 72 |
+
# Check CUDA availability
|
| 73 |
+
if not torch.cuda.is_available():
|
| 74 |
+
logger.error("CUDA is not available. BitsAndBytes quantization requires a GPU to perform the compression.")
|
| 75 |
+
sys.exit(1)
|
| 76 |
+
|
| 77 |
+
logger.info(f"Loading model from '{args.model_dir}' and quantizing to {args.format}...")
|
| 78 |
+
try:
|
| 79 |
+
# Load model
|
| 80 |
+
model = VibeVoiceAsrForConditionalGeneration.from_pretrained(
|
| 81 |
+
args.model_dir,
|
| 82 |
+
quantization_config=quantization_config,
|
| 83 |
+
torch_dtype=torch.bfloat16,
|
| 84 |
+
device_map="auto",
|
| 85 |
+
)
|
| 86 |
+
|
| 87 |
+
# Load processor
|
| 88 |
+
logger.info("Loading processor...")
|
| 89 |
+
processor = AutoProcessor.from_pretrained(args.model_dir)
|
| 90 |
+
|
| 91 |
+
# Save
|
| 92 |
+
logger.info(f"Saving quantized model and processor to '{args.output_dir}'...")
|
| 93 |
+
os.makedirs(args.output_dir, exist_ok=True)
|
| 94 |
+
model.save_pretrained(args.output_dir)
|
| 95 |
+
processor.save_pretrained(args.output_dir)
|
| 96 |
+
|
| 97 |
+
logger.info("Quantization completed successfully!")
|
| 98 |
+
logger.info(f"You can now point your FastAPI server to '{args.output_dir}' to load it instantly.")
|
| 99 |
+
|
| 100 |
+
except Exception as e:
|
| 101 |
+
logger.exception(f"Quantization failed: {e}")
|
| 102 |
+
sys.exit(1)
|
| 103 |
+
|
| 104 |
+
if __name__ == "__main__":
|
| 105 |
+
main()
|
requirements.txt
CHANGED
|
@@ -7,3 +7,5 @@ torchaudio
|
|
| 7 |
fastapi
|
| 8 |
uvicorn
|
| 9 |
requests
|
|
|
|
|
|
|
|
|
| 7 |
fastapi
|
| 8 |
uvicorn
|
| 9 |
requests
|
| 10 |
+
bitsandbytes>=0.43.0
|
| 11 |
+
torchao>=0.6.0
|
tokenizer_config.json
CHANGED
|
@@ -20,7 +20,8 @@
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
| 23 |
-
"is_local":
|
|
|
|
| 24 |
"model_max_length": 131072,
|
| 25 |
"pad_token": "<|endoftext|>",
|
| 26 |
"processor_class": "VibeVoiceAsrProcessor",
|
|
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
"model_max_length": 131072,
|
| 26 |
"pad_token": "<|endoftext|>",
|
| 27 |
"processor_class": "VibeVoiceAsrProcessor",
|