Instructions to use ajibawa-2023/Code-Llama-3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajibawa-2023/Code-Llama-3-8B with Transformers:

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

pipe = pipeline("text-generation", model="ajibawa-2023/Code-Llama-3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ajibawa-2023/Code-Llama-3-8B")
model = AutoModelForCausalLM.from_pretrained("ajibawa-2023/Code-Llama-3-8B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ajibawa-2023/Code-Llama-3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajibawa-2023/Code-Llama-3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajibawa-2023/Code-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ajibawa-2023/Code-Llama-3-8B

SGLang

How to use ajibawa-2023/Code-Llama-3-8B 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 "ajibawa-2023/Code-Llama-3-8B" \
    --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": "ajibawa-2023/Code-Llama-3-8B",
		"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 "ajibawa-2023/Code-Llama-3-8B" \
        --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": "ajibawa-2023/Code-Llama-3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ajibawa-2023/Code-Llama-3-8B with Docker Model Runner:
```
docker model run hf.co/ajibawa-2023/Code-Llama-3-8B
```

Thank you for making this!

by rombodawg - opened May 9, 2024

Discussion

rombodawg

May 9, 2024

Ive been trying to make one of these models myself but have been failing to. Its really hard to finetune correctly as it turns out. Good job!!!

Here is my tweet of your model so everyone can see

https://x.com/dudeman6790/status/1788686507940704267

ajibawa-2023

Owner May 10, 2024

Thank you very much for your kind words @rombodawg . Thank you for the tweet & spreading the word! I am also waiting for humaneval score.

rombodawg

May 10, 2024

@ajibawa-2023 So i have some bad news. The humaneval score did not score much higher than base llama-3-8b. at around .35 points. Sorry to disappoint.

ajibawa-2023

Owner May 10, 2024

No worries man!

ajibawa-2023 changed discussion status to closed May 22, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment