File size: 1,804 Bytes
3e4df52 664c12c 4bbeeb1 3e4df52 664c12c 4bbeeb1 664c12c |
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 |
---
library_name: peft
base_model: tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
language:
- ja
license: apache-2.0
tags:
- text-generation-inference
- transformers
- trl
- mixtral
datasets:
- kunishou/amenokaku-code-instruct
license_name: mixtral
---
# Uploaded model
- **Developed by:** taoki
- **License:** apache-2.0
- **Finetuned from model :** tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
# Usage
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
model_name = "tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(model_name, load_in_4bit=True, torch_dtype=torch.bfloat16)
model = PeftModel.from_pretrained(model, "taoki/Swallow-MX-8x7b-NVE-v0.1-qlora-amenokaku-code-adapter")
prompt="""### Instruction:
紫式部と清少納言の作風をjsonで出力してください。
### Response:
"""
input_ids = tokenizer.encode(
prompt,
add_special_tokens=False,
return_tensors="pt"
)
tokens = model.generate(
input_ids.to(device=model.device),
max_new_tokens=1024,
temperature=0.99,
top_p=0.95,
do_sample=True,
)
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(out)
```
# Output
````
### Instruction:
紫式部と清少納言の作風をjsonで出力してください。
### Response:
```json
{
"紫式部": "貴人に会って、その人が話していることを思い出しながら奏でると、これにまさる楽器はありません。」,
"清少納言": "人によってあげくはなく、おのずからかなしくゆくほどに、かなしみは深くなりゆきなさるなり。」
}
```
````
# Framework versions
- PEFT 0.9.0 |