How to use from the
Use from the
Transformers library
# Gated model: Login with a HF token with gated access permission
hf auth login
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="defiobi00/GLM-5.3-DERISKED-Int4-Int8Mix")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("defiobi00/GLM-5.3-DERISKED-Int4-Int8Mix")
model = AutoModelForCausalLM.from_pretrained("defiobi00/GLM-5.3-DERISKED-Int4-Int8Mix", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
Quick Links

Access request

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This repository is public metadata with a manual download gate. Submit an accurate intended-use statement. Approval is discretionary and may be revoked for misuse or redistribution without authorization.

Log in or Sign Up to review the conditions and access this model content.

GLM-5.3-DERISKED-Int4-Int8Mix

Client drop ยท full GLM-5.3 MoE ยท compressed-tensors pack-quant ยท Blackfrost DWM a=3

Built by Blackfrost ยท Las Vegas, Nevada

Public metadata, manual download gate. Client delivery. Request access on the Hub. Do not redistribute the weights without authorization.

What this is

Independent Int4-Int8Mix pack-quantized safetensors of GLM-5.3 (full ~753B MoE, not Flash) after a Blackfrost direction-weight modification (DWM) pass. Source mix weights were not overwritten.

The intended behavior is in the weights. Production DWM details are proprietary and are not disclosed beyond the locked recipe below.

This artifact has not been through a judged refusal suite. Do not copy NVFP4/BF16/Q3 refusal percentages onto this checkpoint.

Specifications

Architecture GlmMoeDsaForCausalLM (glm_moe_dsa)
Quant compressed-tensors pack-quantized ยท int8 group-128 linears ยท int4 group-128 routed experts ยท layer 0 BF16 ยท MTP int8 channel (stock)
Shards 282 safetensors
Layers 78 main + MTP layer 78
Hidden size 6144
Experts 256 routed ยท top-8 / token ยท 1 shared
DWM alpha 3.0 ยท skip-early 2 ยท one pass ยท frozen scales ยท no norm restore
Targets 76 o_proj + 1 dense down_proj + 19200 expert down_proj + 75 shared down_proj
Runtime vLLM compressed-tensors / pack-quantized (multi-Spark). Not a GGUF.
Languages English and Chinese

Sibling client GGUF (separate repo, do not mix formats): defiobi00/GLM-5.3-DERISKED-UD-Q3_K_XL.

Downloads last month
-
Safetensors
Model size
779B params
Tensor type
I32
ยท
BF16
ยท
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for defiobi00/GLM-5.3-DERISKED-Int4-Int8Mix

Quantized
(36)
this model