Instructions to use Pection/llama3-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pection/llama3-finetune with Transformers:

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

pipe = pipeline("text-generation", model="Pection/llama3-finetune")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pection/llama3-finetune")
model = AutoModelForCausalLM.from_pretrained("Pection/llama3-finetune", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pection/llama3-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pection/llama3-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pection/llama3-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Pection/llama3-finetune

SGLang

How to use Pection/llama3-finetune 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 "Pection/llama3-finetune" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pection/llama3-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Pection/llama3-finetune" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pection/llama3-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Pection/llama3-finetune with Docker Model Runner:
```
docker model run hf.co/Pection/llama3-finetune
```

Pection commited on Nov 27, 2024

Commit

8242bc6

verified ·

1 Parent(s): 4359a3c

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -2

README.md CHANGED Viewed

@@ -4,5 +4,23 @@ tags:
 pipeline_tag: text-generation
 ---
-# My LLaMA Model
-This model is fine-tuned for generating text based on input prompts.

 pipeline_tag: text-generation
 ---
+# LLaMA 3 Fine-Tuned Model
+This is a fine-tuned version of the LLaMA 3 model for [task or dataset]. Below is an example of how to use it:
+## Example Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("YOUR_USERNAME/llama3-finetune")
+model = AutoModelForCausalLM.from_pretrained("YOUR_USERNAME/llama3-finetune")
+# Generate response
+prompt = "Where is Bangkok?"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)