Instructions to use vicky4s4s/llama-3.2-3b-fine-tune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicky4s4s/llama-3.2-3b-fine-tune with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "vicky4s4s/llama-3.2-3b-fine-tune")

Transformers

How to use vicky4s4s/llama-3.2-3b-fine-tune with Transformers:

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

pipe = pipeline("text-generation", model="vicky4s4s/llama-3.2-3b-fine-tune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vicky4s4s/llama-3.2-3b-fine-tune", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vicky4s4s/llama-3.2-3b-fine-tune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicky4s4s/llama-3.2-3b-fine-tune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicky4s4s/llama-3.2-3b-fine-tune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicky4s4s/llama-3.2-3b-fine-tune

SGLang

How to use vicky4s4s/llama-3.2-3b-fine-tune 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 "vicky4s4s/llama-3.2-3b-fine-tune" \
    --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": "vicky4s4s/llama-3.2-3b-fine-tune",
		"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 "vicky4s4s/llama-3.2-3b-fine-tune" \
        --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": "vicky4s4s/llama-3.2-3b-fine-tune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use vicky4s4s/llama-3.2-3b-fine-tune with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vicky4s4s/llama-3.2-3b-fine-tune to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for vicky4s4s/llama-3.2-3b-fine-tune to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for vicky4s4s/llama-3.2-3b-fine-tune to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="vicky4s4s/llama-3.2-3b-fine-tune",
    max_seq_length=2048,
)

Docker Model Runner
How to use vicky4s4s/llama-3.2-3b-fine-tune with Docker Model Runner:
```
docker model run hf.co/vicky4s4s/llama-3.2-3b-fine-tune
```

Model Card for Model ID

Model Details

Model Description



import os
from transformers import pipeline
import torch
import re

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)

base_dir = os.getcwd()
model_id = os.path.join(base_dir,"models" ,"llama-3.2-3b-fine-tune")

print(model_id)
pipe = pipeline("text-generation", model=model_id, torch_dtype=torch.bfloat16, device_map=device)

messages = [
    {"role": "user", "content": "How can I protect myself from HIV and STIs during sex?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=500, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
answer = outputs[0]["generated_text"]
print(answer)

Downloads last month: 4