Llama-3-8B-Instruct-DPO-v0.3 (32k)

This model is a fine-tune (DPO) of meta-llama/Meta-Llama-3-8B-Instruct model. I have used rope_theta to extend the context length up to 32K safely.

Quantized GGUF

All GGUF models come with context length of 32000: Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF

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-3-8B-Instruct-DPO-v0.3 as the model name in Hugging Face's transformers library.

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

model_id = "MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3"

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|>")
]

outputs = pipeline(
 prompt,
 max_new_tokens=8192,
 eos_token_id=terminators,
 do_sample=True,
 temperature=0.6,
 top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Base model