Instructions to use infly/INF-34B-Chat-GPTQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infly/INF-34B-Chat-GPTQ-4bit with Transformers:

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

pipe = pipeline("text-generation", model="infly/INF-34B-Chat-GPTQ-4bit", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("infly/INF-34B-Chat-GPTQ-4bit", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use infly/INF-34B-Chat-GPTQ-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/INF-34B-Chat-GPTQ-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/INF-34B-Chat-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infly/INF-34B-Chat-GPTQ-4bit

SGLang

How to use infly/INF-34B-Chat-GPTQ-4bit 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 "infly/INF-34B-Chat-GPTQ-4bit" \
    --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": "infly/INF-34B-Chat-GPTQ-4bit",
		"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 "infly/INF-34B-Chat-GPTQ-4bit" \
        --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": "infly/INF-34B-Chat-GPTQ-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use infly/INF-34B-Chat-GPTQ-4bit with Docker Model Runner:
```
docker model run hf.co/infly/INF-34B-Chat-GPTQ-4bit
```

INF-34B-Chat-GPTQ-4bit / config.json

stgzr

update tokenizer & model weights

5d1d4ec verified about 2 years ago

Raw

History Blame Contribute Delete

1.08 kB

	{
	"architectures": [
	"INFLMForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_inflm.INFLMConfig",
	"AutoModelForCausalLM": "modeling_inflm.INFLMForCausalLM"
	},
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 8192,
	"initializer_range": 0.02,
	"intermediate_size": 22016,
	"layer_norm_eps": 1e-05,
	"max_position_embeddings": 32768,
	"mlp_bias": false,
	"model_type": "inflm",
	"num_attention_heads": 64,
	"num_hidden_layers": 48,
	"num_key_value_heads": 8,
	"pretraining_tp": 1,
	"quantization_config": {
	"bits": 4,
	"checkpoint_format": "gptq",
	"damp_percent": 0.1,
	"desc_act": false,
	"group_size": 128,
	"model_file_base_name": "model",
	"model_name_or_path": null,
	"quant_method": "gptq",
	"static_groups": false,
	"sym": true,
	"true_sequential": true
	},
	"rope_scaling": null,
	"rope_theta": 500000,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"use_cache": true,
	"vocab_size": 96512
	}