Instructions to use abbatea/Tutorbot-variation-DPO-Llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abbatea/Tutorbot-variation-DPO-Llama 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, "abbatea/Tutorbot-variation-DPO-Llama")

Transformers

How to use abbatea/Tutorbot-variation-DPO-Llama with Transformers:

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

pipe = pipeline("text-generation", model="abbatea/Tutorbot-variation-DPO-Llama")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("abbatea/Tutorbot-variation-DPO-Llama", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abbatea/Tutorbot-variation-DPO-Llama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abbatea/Tutorbot-variation-DPO-Llama

SGLang

How to use abbatea/Tutorbot-variation-DPO-Llama 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 "abbatea/Tutorbot-variation-DPO-Llama" \
    --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": "abbatea/Tutorbot-variation-DPO-Llama",
		"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 "abbatea/Tutorbot-variation-DPO-Llama" \
        --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": "abbatea/Tutorbot-variation-DPO-Llama",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abbatea/Tutorbot-variation-DPO-Llama with Docker Model Runner:
```
docker model run hf.co/abbatea/Tutorbot-variation-DPO-Llama
```

Model Card for Model ID

Model Card for Llama_DPO_lora

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct. It has been trained using DPO. The dataset it was build upon is a combination on MathDial dataset and generated model responses using MathDial as an input.

The model is optimized for:

Conversational math problem solving
Step-by-step reasoning in dialogue form
Scaffolding

Repository: Github code DPO Training and Datasets

Intended Use

This model is intended for use in:

Interactive math tutoring
Research in dialogue-based problem solving
Educational tools

Example Usage


import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

# Base model
basemodelname = "meta-llama/Llama-3.1-8B-Instruct"
base_model = AutoModelForCausalLM.from_pretrained(
    basemodelname,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load adapter on top
peft_model_path = "abbatea/Tutorbot-variation-DPO-Llama"
model = PeftModel.from_pretrained(base_model, peft_model_path)

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(basemodelname)
if tokenizer.pad_token is None:
    tokenizer.pad_token = tokenizer.eos_token
    tokenizer.pad_token_id = tokenizer.eos_token_id



messages = [
    {"role": "user", "content": "Can you help me solve 3x + 5 = 20?"}
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Citations

DPO:

@inproceedings{rafailov2023direct,
    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}

Downloads last month: 3

Model tree for abbatea/Tutorbot-variation-DPO-Llama

Base model

meta-llama/Llama-3.1-8B

Finetuned

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

Adapter

(2386)

this model