File size: 1,747 Bytes
5258dc6 0354728 5258dc6 0354728 5258dc6 |
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 |
---
library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
- text: Hello!
example_title: Hello world
group: Python
---
This model is for debugging. It is randomly initialized using the config from [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) but with smaller size.
Codes:
```python
import transformers
import torch
import os
from huggingface_hub import create_repo, upload_folder
import accelerate
model_id = 'Qwen/Qwen2.5-72B-Instruct'
save_path = '/tmp/yujiepan/qwen2.5-tiny-random'
repo_id = 'yujiepan/qwen2.5-tiny-random'
os.system(f'rm -rf {save_path}')
config = transformers.AutoConfig.from_pretrained(
model_id,
trust_remote_code=True,
)
config._name_or_path = model_id
config.hidden_size = 8
config.intermediate_size = 16
config.num_key_value_heads = 2
config.num_attention_heads = 4
config.num_hidden_layers = 2
config.max_window_layers = 1
transformers.set_seed(42)
model = transformers.AutoModelForCausalLM.from_config(
config,
trust_remote_code=True,
)
model.generation_config = transformers.GenerationConfig.from_pretrained(
model_id)
model = model.to(torch.bfloat16)
transformers.set_seed(42)
with torch.no_grad():
for p in model.parameters():
torch.nn.init.normal_(p)
model.save_pretrained(save_path)
tokenizer = transformers.AutoTokenizer.from_pretrained(
model_id,
trust_remote_code=True,
)
tokenizer.save_pretrained(save_path)
output = model.float().generate(torch.tensor(
[[1, 2, 3]]).long(), max_length=16, do_sample=True)
os.system(f'ls -alh {save_path}')
# os.system(f'rm -rf {save_path}/model.safetensors')
# create_repo(repo_id, exist_ok=True)
# upload_folder(repo_id=repo_id, folder_path=save_path)
```
|