Instructions to use cmarkea/CodeLlama-34b-Instruct-hf-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmarkea/CodeLlama-34b-Instruct-hf-4bit with Transformers:

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

pipe = pipeline("text-generation", model="cmarkea/CodeLlama-34b-Instruct-hf-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cmarkea/CodeLlama-34b-Instruct-hf-4bit")
model = AutoModelForCausalLM.from_pretrained("cmarkea/CodeLlama-34b-Instruct-hf-4bit")
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

vLLM

How to use cmarkea/CodeLlama-34b-Instruct-hf-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmarkea/CodeLlama-34b-Instruct-hf-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": "cmarkea/CodeLlama-34b-Instruct-hf-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cmarkea/CodeLlama-34b-Instruct-hf-4bit

SGLang

How to use cmarkea/CodeLlama-34b-Instruct-hf-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 "cmarkea/CodeLlama-34b-Instruct-hf-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": "cmarkea/CodeLlama-34b-Instruct-hf-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 "cmarkea/CodeLlama-34b-Instruct-hf-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": "cmarkea/CodeLlama-34b-Instruct-hf-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cmarkea/CodeLlama-34b-Instruct-hf-4bit with Docker Model Runner:
```
docker model run hf.co/cmarkea/CodeLlama-34b-Instruct-hf-4bit
```

Cyrile commited on Nov 14, 2024

Commit

035354f

verified ·

1 Parent(s): c959aec

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -21,6 +21,9 @@ even if the response was technically correct.
 | gemini-1.5-pro                                  | 4.51     | NA                 | NA        |
 | gpt-4o                                          | 4.51     | NA                 | NA        |
 | claude3.5-sonnet                                | 4.49     | NA                 | NA        |
 | deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct     | 4.24     | 15.7               | 31.4      |
 | meta-llama/Meta-Llama-3.1-70B-Instruct          | 4.23     | 70.06              | 140.12    |
 | cmarkea/Meta-Llama-3.1-70B-Instruct-4bit        | 4.14     | 70.06              | 35.3      |

 | gemini-1.5-pro                                  | 4.51     | NA                 | NA        |
 | gpt-4o                                          | 4.51     | NA                 | NA        |
 | claude3.5-sonnet                                | 4.49     | NA                 | NA        |
+| Qwen/Qwen2.5-Coder-32B-Instruct                 | 4.41     | 32.8               | 65.6      |
+| Qwen/Qwen2.5-32B-Instruct	                      | 4.40     | 32.8               | 65.6      |
+| cmarkea/Qwen2.5-32B-Instruct-4bit               | 4.36     | 32.8               | 16.4      |
 | deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct     | 4.24     | 15.7               | 31.4      |
 | meta-llama/Meta-Llama-3.1-70B-Instruct          | 4.23     | 70.06              | 140.12    |
 | cmarkea/Meta-Llama-3.1-70B-Instruct-4bit        | 4.14     | 70.06              | 35.3      |