File size: 1,785 Bytes
5d63f52 |
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 |
---
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 [tiiuae/falcon-mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b) but with smaller size.
Codes:
```python
import os
import torch
from huggingface_hub import create_repo, upload_folder
from transformers import (
AutoModelForCausalLM,
AutoTokenizer,
GenerationConfig,
AutoConfig,
pipeline,
set_seed,
)
model_id = "tiiuae/falcon-mamba-7b"
repo_id = "yujiepan/falcon-mamba-tiny-random"
save_path = f"/tmp/{repo_id}"
os.system(f'rm -rf {save_path}')
config = AutoConfig.from_pretrained(model_id)
config.use_cache = True
config.num_hidden_layers = 2
config.hidden_size = 8
config.intermediate_size = 16
config.state_size = 8
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)
model = AutoModelForCausalLM.from_config(
config, torch_dtype=torch.bfloat16,
trust_remote_code=True,
)
model.generation_config = GenerationConfig.from_pretrained(
model_id,
trust_remote_code=True,
)
set_seed(42)
num_params = 0
with torch.no_grad():
for name, p in sorted(model.named_parameters()):
print(name, p.shape)
torch.nn.init.uniform_(p, -0.5, 0.5)
num_params += p.numel()
print("Total number of parameters:", num_params)
model.save_pretrained(save_path)
pipe = pipeline(
"text-generation",
model=save_path,
device="cpu",
trust_remote_code=True,
max_new_tokens=20,
)
print(pipe("Hello World!"))
# create_repo(repo_id, exist_ok=True)
# upload_folder(repo_id=repo_id, folder_path=save_path, repo_type='model')
```
|