File size: 1,665 Bytes
04f34cc |
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 |
---
pipeline_tag: text-generation
inference: true
widget:
- text: 'Hello!'
example_title: Hello world
group: Python
library_name: transformers
---
This model is randomly initialized, using the config from [internlm/internlm2-chat-20b](https://huggingface.co/internlm/internlm2-chat-20b/blob/main/config.json) but with smaller size.
Note the model is in float16.
Codes:
```python
import transformers
import torch
import os
from huggingface_hub import create_repo, upload_folder
source_model_id = 'internlm/internlm2-chat-20b'
tiny_random_name = 'internlm2-tiny-random'
save_path = f'/tmp/yujiepan/{tiny_random_name}'
repo_id = f'yujiepan/{tiny_random_name}'
config = transformers.AutoConfig.from_pretrained(
source_model_id, trust_remote_code=True)
config.hidden_size = 4
config.intermediate_size = 6
config.num_attention_heads = 4
config.num_key_value_heads = 2
config.num_hidden_layers = 2
config.torch_dtype = torch.float16
model = transformers.AutoModelForCausalLM.from_config(
config, trust_remote_code=True, torch_dtype=torch.float16)
model = model.half()
tokenizer = transformers.AutoTokenizer.from_pretrained(
source_model_id, trust_remote_code=True)
result = transformers.pipelines.pipeline(
'text-generation',
model=model, tokenizer=tokenizer,
device=0,
max_new_tokens=16,
)('Hello')
print(result)
# model = model.cuda()
# response, history = model.chat(tokenizer, "Hi", history=[], max_length=32)
# print(response)
model.save_pretrained(save_path)
tokenizer.save_pretrained(save_path)
os.system(f'ls -alh {save_path}')
create_repo(repo_id, exist_ok=True)
upload_folder(repo_id=repo_id, folder_path=save_path)
```
|