👑 Llama-3
Collection
My experiments with Llama-3 models
•
59 items
•
Updated
•
22
This model is a fine-tune (DPO) of meta-llama/Meta-Llama-3-8B-Instruct
model.
All GGUF models are available here: Llama-3-8B-Instruct-DPO-v0.4-GGUF
This model uses ChatML
prompt template:
<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}
You can use this model by using MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.4
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-v0.4"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
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=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 68.49 |
AI2 Reasoning Challenge (25-Shot) | 62.54 |
HellaSwag (10-Shot) | 79.73 |
MMLU (5-Shot) | 68.08 |
TruthfulQA (0-shot) | 53.94 |
Winogrande (5-shot) | 75.61 |
GSM8k (5-shot) | 71.04 |