File size: 1,599 Bytes
73b6b3a 4d77746 73b6b3a 4d77746 73b6b3a |
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 |
---
library_name: transformers
pipeline_tag: text-generation
inference: true
widget:
- text: Hello!
example_title: Hello world
group: Python
---
This model is randomly initialized, using the config from [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) but with smaller size.
Codes:
```python
from optimum.intel.openvino import OVModelForCausalLM
from transformers import pipeline
from huggingface_hub import create_repo, upload_folder
import torch
import transformers
import os
model_id = 'mistralai/Mixtral-8x7B-v0.1'
save_path = '/tmp/yujiepan/mixtral-8xtiny-random'
repo_id = 'yujiepan/mixtral-8xtiny-random'
config = transformers.AutoConfig.from_pretrained(model_id)
config.hidden_size = 8
config.intermediate_size = 32
config.num_attention_heads = 4
config.num_experts_per_tok = 2
config.num_hidden_layers = 2
config.num_key_value_heads = 2
config.num_local_experts = 8
print(config)
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
tokenizer.save_pretrained(save_path)
model = transformers.AutoModelForCausalLM.from_config(config, torch_dtype=torch.float16)
model = model.half()
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, do_sample=False, device='cuda')
print(pipe('Hello World!'))
model.save_pretrained(save_path)
# ovmodel = OVModelForCausalLM.from_pretrained(save_path, export=True)
# ovmodel = ovmodel.half()
# ovmodel.save_pretrained(save_path)
os.system(f'ls -alh /tmp/yujiepan/mixtral-8xtiny-random')
create_repo(repo_id, exist_ok=True)
upload_folder(repo_id=repo_id, folder_path=save_path)
```
|