Instructions to use Infi-MM/infimm-zephyr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infi-MM/infimm-zephyr with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Infi-MM/infimm-zephyr", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Infi-MM/infimm-zephyr", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Infi-MM/infimm-zephyr with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infi-MM/infimm-zephyr"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infi-MM/infimm-zephyr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Infi-MM/infimm-zephyr

SGLang

How to use Infi-MM/infimm-zephyr with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Infi-MM/infimm-zephyr" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infi-MM/infimm-zephyr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Infi-MM/infimm-zephyr" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infi-MM/infimm-zephyr",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Infi-MM/infimm-zephyr with Docker Model Runner:
```
docker model run hf.co/Infi-MM/infimm-zephyr
```

infimm-zephyr / config.json

xiaotianhan

Upload folder using huggingface_hub

779abe8 over 2 years ago

Raw

History Blame Contribute Delete

1.89 kB

	{
	"_name_or_path": "./",
	"architectures": [
	"InfiMMZephyrModel"
	],
	"auto_map": {
	"AutoConfig": "configuration_infimm_zephyr.InfiMMConfig",
	"AutoModelForCausalLM": "modeling_infimm_zephyr.InfiMMZephyrModel"
	},
	"model_type": "infimm-zephyr",
	"seq_length": 1024,
	"tokenizer_type": "LlamaTokenizer",
	"torch_dtype": "bfloat16",
	"transformers_version": "4.35.2",
	"use_cache": true,
	"use_flash_attn": false,
	"cross_attn_every_n_layers": 2,
	"use_grad_checkpoint": false,
	"freeze_llm": true,
	"image_token_id": 32001,
	"eoc_token_id": 32000,
	"visual": {
	"image_size": 336,
	"layers": 24,
	"width": 1024,
	"head_width": 64,
	"patch_size": 14,
	"mlp_ratio": 2.6667,
	"eva_model_name": "eva-clip-l-14-336",
	"drop_path_rate": 0.0,
	"xattn": false,
	"fusedLN": true,
	"rope": true,
	"pt_hw_seq_len": 16,
	"intp_freq": true,
	"naiveswiglu": true,
	"subln": true,
	"embed_dim": 768
	},
	"language": {
	"_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
	"architectures": [
	"MistralForCausalLM"
	],
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"max_position_embeddings": 32768,
	"model_type": "mistral",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"pad_token_id": 2,
	"rms_norm_eps": 1e-05,
	"rope_theta": 10000.0,
	"sliding_window": 4096,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.35.0",
	"use_cache": true,
	"vocab_size": 32002
	}
	}