File size: 2,388 Bytes
ae440e5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
# NanoLM-1B-Instruct-v1.1
[English](README.md) | 简体中文
## Introduction
为了探究小模型的潜能，我尝试构建一系列小模型，并存放于 [NanoLM Collections](https://huggingface.co/collections/Mxode/nanolm-66d6d75b4a69536bca2705b2)。
这是 NanoLM-1B-Instruct-v1.1。该模型目前仅支持**英文**。
## 模型详情
| Nano LMs | Non-emb Params | Arch | Layers | Dim | Heads | Seq Len |
| :----------: | :------------------: | :---: | :----: | :-------: | :---: | :---: |
| 25M | 15M | MistralForCausalLM | 12 | 312 | 12 | 2K |
| 70M | 42M | LlamaForCausalLM | 12 | 576 | 9 |2K|
| 0.3B | 180M | Qwen2ForCausalLM | 12 | 896 | 14 |4K|
| **1B** | **840M** | **Qwen2ForCausalLM** | **18** | **1536** | **12** | **4K** |
## 如何使用
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = 'Mxode/NanoLM-1B-Instruct-v1.1'
model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)
def get_response(prompt: str, **kwargs):
generation_args = dict(
max_new_tokens = kwargs.pop("max_new_tokens", 512),
do_sample = kwargs.pop("do_sample", True),
temperature = kwargs.pop("temperature", 0.7),
top_p = kwargs.pop("top_p", 0.8),
top_k = kwargs.pop("top_k", 40),
**kwargs
)
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(model_inputs.input_ids, **generation_args)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
return response
prompt = "Calculate (4 - 1)^(9 - 5)"
print(get_response(prompt, do_sample=False))
"""
The expression (4 - 1)^(9 - 5) can be simplified as follows:
(4 - 1) = 3
So the expression becomes 3^(9 - 5)
3^(9 - 5) = 3^4
3^4 = 81
Therefore, (4 - 1)^(9 - 5) = 81.
"""
```
|