Instructions to use HenryJJ/llama3-8B-lima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HenryJJ/llama3-8B-lima with Transformers:

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

pipe = pipeline("text-generation", model="HenryJJ/llama3-8B-lima")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HenryJJ/llama3-8B-lima")
model = AutoModelForCausalLM.from_pretrained("HenryJJ/llama3-8B-lima")
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 HenryJJ/llama3-8B-lima with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HenryJJ/llama3-8B-lima"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HenryJJ/llama3-8B-lima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HenryJJ/llama3-8B-lima

SGLang

How to use HenryJJ/llama3-8B-lima 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 "HenryJJ/llama3-8B-lima" \
    --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": "HenryJJ/llama3-8B-lima",
		"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 "HenryJJ/llama3-8B-lima" \
        --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": "HenryJJ/llama3-8B-lima",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HenryJJ/llama3-8B-lima with Docker Model Runner:
```
docker model run hf.co/HenryJJ/llama3-8B-lima
```

llama3-8B-lima

SFT with 64bits/lima_vicuna_format. 3 epoch qlora. Code under https://huggingface.co/HenryJJ/llama3-8B-lima/blob/main/config/llama3-lima.yml.

Model Details

Trained by: trained by HenryJJ.
Model type: llama3 is an auto-regressive language model based on the Llama 3 transformer architecture.
Language(s): English
License for llama3-8B-lima: apache-2.0 license

Prompting

Prompt format chatml: This model uses ChatML prompt format.

<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Example:

<|im_start|>system
You are a helpful assistant.
<|im_start|>user
who is the president of us
<|im_start|>assistant

Downloads last month: 9

HenryJJ
/

llama3-8B-lima

llama3-8B-lima

Model Details

Prompting

Dataset used to train HenryJJ/llama3-8B-lima