Llama-3-70B-Instruct-DPO-v0.1 / README.md

Update README.md (#11)

789c8d6 verified about 1 month ago

No virus

6.19 kB

	---
	language:
	- en
	license: llama3
	library_name: transformers
	tags:
	- axolotl
	- finetune
	- dpo
	- facebook
	- meta
	- pytorch
	- llama
	- llama-3
	- chatml
	base_model: meta-llama/Meta-Llama-3-70B-Instruct
	datasets:
	- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
	model_name: Llama-3-70B-Instruct-DPO-v0.1
	pipeline_tag: text-generation
	license_name: llama3
	license_link: LICENSE
	inference: false
	model_creator: MaziyarPanahi
	quantized_by: MaziyarPanahi
	model-index:
	- name: Llama-3-70B-Instruct-DPO-v0.1
	results:
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: AI2 Reasoning Challenge (25-Shot)
	type: ai2_arc
	config: ARC-Challenge
	split: test
	args:
	num_few_shot: 25
	metrics:
	- type: acc_norm
	value: 71.67
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: HellaSwag (10-Shot)
	type: hellaswag
	split: validation
	args:
	num_few_shot: 10
	metrics:
	- type: acc_norm
	value: 85.83
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MMLU (5-Shot)
	type: cais/mmlu
	config: all
	split: test
	args:
	num_few_shot: 5
	metrics:
	- type: acc
	value: 80.12
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: TruthfulQA (0-shot)
	type: truthful_qa
	config: multiple_choice
	split: validation
	args:
	num_few_shot: 0
	metrics:
	- type: mc2
	value: 62.11
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: Winogrande (5-shot)
	type: winogrande
	config: winogrande_xl
	split: validation
	args:
	num_few_shot: 5
	metrics:
	- type: acc
	value: 82.87
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: GSM8k (5-shot)
	type: gsm8k
	config: main
	split: test
	args:
	num_few_shot: 5
	metrics:
	- type: acc
	value: 86.05
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1
	name: Open LLM Leaderboard
	---

	<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-DPO-v0.1

	This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.

	# ⚡ Quantized GGUF

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

	# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.1)

	\| Metric \|Value\|
	\|---------------------------------\|----:\|
	\|Avg. \|78.11\|
	\|AI2 Reasoning Challenge (25-Shot)\|71.67\|
	\|HellaSwag (10-Shot) \|85.83\|
	\|MMLU (5-Shot) \|80.12\|
	\|TruthfulQA (0-shot) \|62.11\|
	\|Winogrande (5-shot) \|82.87\|
	\|GSM8k (5-shot) \|86.05\|

	Top 10 models on the Leaderboard
	<img src="./llama-3-70b-top-10.png" alt="Llama-3-70B finet-tuned models" style="margin-left:'auto' margin-right:'auto' display:'block'"/>


	# 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-DPO-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-DPO-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("<\|im_end\|>"),
	tokenizer.convert_tokens_to_ids("<\|eot_id\|>") # safer to have this too
	]

	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):])
	```