Instructions to use thesven/Llama3-8B-SFT-code_bagel-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thesven/Llama3-8B-SFT-code_bagel-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="thesven/Llama3-8B-SFT-code_bagel-bnb-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thesven/Llama3-8B-SFT-code_bagel-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("thesven/Llama3-8B-SFT-code_bagel-bnb-4bit")
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 Settings

vLLM

How to use thesven/Llama3-8B-SFT-code_bagel-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thesven/Llama3-8B-SFT-code_bagel-bnb-4bit

SGLang

How to use thesven/Llama3-8B-SFT-code_bagel-bnb-4bit 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 "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit" \
    --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": "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit",
		"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 "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit" \
        --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": "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thesven/Llama3-8B-SFT-code_bagel-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/thesven/Llama3-8B-SFT-code_bagel-bnb-4bit
```

Model Card for Llama 3 8B SFT Code Bagel

Model Details

Model Description

This model, Llama3-8B-SFT-code_bagel-bnb-4bit, is a fine-tuned version of the Meta-Llama-3-8B-Instruct model, finetuned via SFT on 35k randomly selected rows from the Replete-AI/code_bagel dataset using Supervised Fine-Tuning (SFT) and quantized to 4-bit precision using the Bits and Bytes (bnb) library. It is optimized for code-related tasks.

Uses

Coding and code related tasks

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

import torch
import transformers

# Load the tokenizer and model
model_id = "thesven/Llama3-8B-SFT-code_bagel-bnb-4bit"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": "Write me a python function to turn every other letter in a string to uppercase?",
    },
]

prompt = pipeline.tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>"),
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.1,
)
print(outputs[0]["generated_text"][len(prompt) :])

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

F16

Dataset used to train thesven/Llama3-8B-SFT-code_bagel-bnb-4bit

Spaces using thesven/Llama3-8B-SFT-code_bagel-bnb-4bit 2

Collection including thesven/Llama3-8B-SFT-code_bagel-bnb-4bit

Finetune

Collection

10 items • Updated Mar 2