Fireball-Llama-3.1-8B-Instruct-v1dpo

Uploaded model

• Developed by: EpistemeAI
• License: apache-2.0
• Finetuned from model : EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1-16bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

<img src="https://huggingface.co/EpistemeAI/Fireball-Llama-3.1-8B-v1dpo/resolve/main/fireball-llama.JPG" width="200"/>

Fireball-Llama-3.1-V1-Instruct

How to use

This repository contains Fireball-Llama-3.11-V1-Instruct , for use with transformers and with the original llama codebase.

Use with transformers

Starting with transformers >= 4.43.0 onward, you can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.

Make sure to update your transformers installation via pip install --upgrade transformers. Example:

!pip install -U transformers trl peft accelerate bitsandbytes

import torch
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
)

base_model = "EpistemeAI/Fireball-Llama-3.1-8B-Instruct-v1dpo"
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(base_model)

sys = "You are help assistant " \
    "(Advanced Natural-based interaction for the language)."

messages = [
    {"role": "system", "content": sys},
    {"role": "user", "content": "What is DPO and ORPO fine tune?"},
]

#Method 1
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
for k,v in inputs.items():
    inputs[k] = v.cuda()
outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_p=0.9, temperature=0.6)
results = tokenizer.batch_decode(outputs)[0]
print(results)

#Method 2
import transformers
pipe = transformers.pipeline(
    model=model,
    tokenizer=tokenizer,
    return_full_text=False, # langchain expects the full text
    task='text-generation',
    max_new_tokens=512, # max number of tokens to generate in the output
    temperature=0.6,  #temperature for more or less creative answers
    do_sample=True,
    top_p=0.9,
)

sequences = pipe(messages)
for seq in sequences:
    print(f"{seq['generated_text']}")