Instructions to use doupari/Llama-3.1-8B-Instruct-question with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use doupari/Llama-3.1-8B-Instruct-question with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "doupari/Llama-3.1-8B-Instruct-question")

Transformers

How to use doupari/Llama-3.1-8B-Instruct-question with Transformers:

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

pipe = pipeline("text-generation", model="doupari/Llama-3.1-8B-Instruct-question")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("doupari/Llama-3.1-8B-Instruct-question", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use doupari/Llama-3.1-8B-Instruct-question with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "doupari/Llama-3.1-8B-Instruct-question"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "doupari/Llama-3.1-8B-Instruct-question",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/doupari/Llama-3.1-8B-Instruct-question

SGLang

How to use doupari/Llama-3.1-8B-Instruct-question 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 "doupari/Llama-3.1-8B-Instruct-question" \
    --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": "doupari/Llama-3.1-8B-Instruct-question",
		"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 "doupari/Llama-3.1-8B-Instruct-question" \
        --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": "doupari/Llama-3.1-8B-Instruct-question",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use doupari/Llama-3.1-8B-Instruct-question with Docker Model Runner:
```
docker model run hf.co/doupari/Llama-3.1-8B-Instruct-question
```

Llama-3.1-8B-Instruct-question LoRA Adapter

This repository contains a LoRA adapter fine-tuned from meta-llama/Llama-3.1-8B-Instruct.

Checkpoint Selection

The uploaded adapter was selected from:

checkpoint: checkpoint-280
global step: 280
epoch: 2.0
metric: eval_loss
best eval loss: 0.0648028627038002

Evaluation loss history from training:

Step	Epoch	Eval loss
140	1.0	0.072911650
280	2.0	0.064802863
420	3.0	0.077800997
560	4.0	0.091106474
700	5.0	0.114740528

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "meta-llama/Llama-3.1-8B-Instruct"
adapter_id = "YOUR_USERNAME/YOUR_REPO_NAME"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    device_map="auto",
    torch_dtype="auto",
)
model = PeftModel.from_pretrained(model, adapter_id)

messages = [{"role": "user", "content": "Your question here"}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 2

Model tree for doupari/Llama-3.1-8B-Instruct-question

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Adapter

(2725)

this model

Collection including doupari/Llama-3.1-8B-Instruct-question

Veri-Graph

Collection

12 items • Updated Jun 24