Views
No views yet
meta-llama/Meta-Llama-3-8B-Instruct model.ChatML prompt template:<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2 as the model name in Hugging Face's
transformers library.1from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
2from transformers import pipeline
3import torch
4
5model_id = "MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.2"
6
7model = AutoModelForCausalLM.from_pretrained(
8 model_id,
9 torch_dtype=torch.bfloat16,
10 device_map="auto",
11 trust_remote_code=True,
12 # attn_implementation="flash_attention_2"
13)
14
15tokenizer = AutoTokenizer.from_pretrained(
16 model_id,
17 trust_remote_code=True
18)
19
20streamer = TextStreamer(tokenizer)
21
22pipeline = pipeline(
23 "text-generation",
24 model=model,
25 tokenizer=tokenizer,
26 model_kwargs={"torch_dtype": torch.bfloat16},
27 streamer=streamer
28)
29
30# Then you can use the pipeline to generate text.
31
32messages = [
33 {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
34 {"role": "user", "content": "Who are you?"},
35]
36
37prompt = tokenizer.apply_chat_template(
38 messages,
39 tokenize=False,
40 add_generation_prompt=True
41)
42
43terminators = [
44 tokenizer.eos_token_id,
45 tokenizer.convert_tokens_to_ids("<|im_end|>")
46]
47
48outputs = pipeline(
49 prompt,
50 max_new_tokens=256,
51 eos_token_id=terminators,
52 do_sample=True,
53 temperature=0.6,
54 top_p=0.95,
55)
56print(outputs[0]["generated_text"][len(prompt):])| Metric | Value |
|---|---|
| Avg. | 68.36 |
| AI2 Reasoning Challenge (25-Shot) | 62.46 |
| HellaSwag (10-Shot) | 79.50 |
| MMLU (5-Shot) | 68.21 |
| TruthfulQA (0-shot) | 53.27 |
| Winogrande (5-shot) | 75.93 |
| GSM8k (5-shot) | 70.81 |