Instructions to use Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw")
model = AutoModelForCausalLM.from_pretrained("Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw

SGLang

How to use Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw 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 "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw" \
    --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": "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw",
		"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 "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw" \
        --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": "Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw with Docker Model Runner:
```
docker model run hf.co/Dracones/CodeQwen1.5-7B-Chat_exl2_8.0bpw
```

Dracones commited on Apr 16, 2024

Commit

36a169d

verified ·

1 Parent(s): a98463f

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -28,7 +28,17 @@ If you have problems loading these models, please update Text Generation WebUI t
 Below are the perplexity scores for the EXL2 models. A lower score is better.
-_TODO:_ Coming soon
 ### Perplexity Script

 Below are the perplexity scores for the EXL2 models. A lower score is better.
+| Quant Level | Perplexity Score |
+|-------------|------------------|
+| 8.0 | 13.6136 |
+| 7.0 | 13.6220 |
+| 6.0 | 13.6524 |
+| 5.0 | 13.7689 |
+| 4.0 | 13.9466 |
+| 3.5 | 14.2961 |
+| 3.0 | 16.8038 |
+| 2.75 | 16.9662 |
+| 2.5 | 17.4515 |
 ### Perplexity Script