File size: 1,689 Bytes
b1b1f85 |
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 |
---
library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
- text: Hello!
example_title: Hello world
group: Python
---
This tiny model is for debugging. It is randomly initialized with the config adapted from [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B).
### Example usage:
```python
from transformers import pipeline
model_id = "yujiepan/qwq-tiny-random-dim64"
pipe = pipeline(
"text-generation", model=model_id, device="cuda",
trust_remote_code=True, max_new_tokens=3,
)
print(pipe("Hello World!"))
```
### Codes to create this repo:
```python
import torch
from transformers import (
AutoConfig,
AutoModelForCausalLM,
AutoTokenizer,
GenerationConfig,
pipeline,
set_seed,
)
source_model_id = "Qwen/QwQ-32B"
save_folder = "/tmp/yujiepan/qwq-tiny-random-dim64"
tokenizer = AutoTokenizer.from_pretrained(
source_model_id, trust_remote_code=True,
)
tokenizer.save_pretrained(save_folder)
config = AutoConfig.from_pretrained(
source_model_id, trust_remote_code=True,
)
config._name_or_path = source_model_id
config.hidden_size = 64
config.intermediate_size = 64
config.num_key_value_heads = 1
config.num_attention_heads = 2
config.num_hidden_layers = 2
config.max_window_layers = 1
model = AutoModelForCausalLM.from_config(
config,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
)
model.generation_config = GenerationConfig.from_pretrained(
source_model_id, trust_remote_code=True,
)
set_seed(42)
with torch.no_grad():
for name, p in sorted(model.named_parameters()):
torch.nn.init.normal_(p, 0, 0.5)
print(name, p.shape)
model.save_pretrained(save_folder)
``` |