README.md

---
language:
- en
license: llama3
library_name: transformers
tags:
- axolotl
- finetune
- facebook
- meta
- pytorch
- llama
- llama-3
- chatml
base_model: meta-llama/Meta-Llama-3-70B-Instruct
datasets:
- MaziyarPanahi/truthy-dpo-v0.1-axolotl
model_name: Llama-3-70B-Instruct-v0.1
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
---

<img src="./llama-3-merges.webp" alt="Llama-3 DPO Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>


# MaziyarPanahi/Llama-3-70B-Instruct-v0.1

This model is a fine-tune of `meta-llama/Meta-Llama-3-70B-Instruct` model. This version comes with `<|im_start|>` and `<|im_end|>` as extra tokens to avoid taking up extra tokens via ChatML prompt.

# ⚡ Quantized GGUF

All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-v0.1-GGUF)

# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
coming soon.

# Prompt Template

This model uses `ChatML` prompt template:

```
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
````

# How to use

You can use this model by using `MaziyarPanahi/Llama-3-70B-Instruct-v0.1` as the model name in Hugging Face's
transformers library.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline
import torch

model_id = "MaziyarPanahi/Llama-3-70B-Instruct-v0.1"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
    # attn_implementation="flash_attention_2"
)

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True
)

streamer = TextStreamer(tokenizer)

pipeline = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    model_kwargs={"torch_dtype": torch.bfloat16},
    streamer=streamer
)

# Then you can use the pipeline to generate text.

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

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

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

outputs = pipeline(
    prompt,
    max_new_tokens=2048,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
```