Instructions to use Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8

SGLang

How to use Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 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 "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8" \
    --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": "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8",
		"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 "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8" \
        --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": "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8 with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-Int8
```

JustinLin610 commited on Nov 18, 2024

Commit

77324e4

1 Parent(s): 391a51f

update tokenizer_config.json,config.json,generation_config.json

Browse files

Files changed (3) hide show

config.json +2 -2
generation_config.json +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -10,7 +10,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 32768,
-  "max_window_layers": 70,
   "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
@@ -44,7 +44,7 @@
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.3",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

   "initializer_range": 0.02,
   "intermediate_size": 11008,
   "max_position_embeddings": 32768,
+  "max_window_layers": 36,
   "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "float16",
+  "transformers_version": "4.43.1",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json CHANGED Viewed

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.39.3"
 }

   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
+  "transformers_version": "4.43.1"
 }

tokenizer_config.json CHANGED Viewed

@@ -199,7 +199,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",