51 lines
1.8 KiB
Markdown
51 lines
1.8 KiB
Markdown
|
---
|
|||
|
|
library_name: transformers
|
|||
|
|
tags:
|
|||
|
|
- trl
|
|||
|
|
- sft
|
|||
|
|
datasets:
|
|||
|
|
- Vikhrmodels/Veles-2.5
|
|||
|
|
- dichspace/darulm
|
|||
|
|
- zjkarina/Vikhr_instruct
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# Veles Instruct [DONT TOUCH, Under Dev]
|
|||
|
|
|
|||
|
|
Просто лучшая русская инстракт модель теперь с CHATML
|
|||
|
|
|
|||
|
|
Метрики, DPO, коды для запуска подьедут позже, мне если честно похуй, вам думаю вообще поебать
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
Самый быстрый старт: https://colab.research.google.com/drive/10g5LSuzwsGVCCtiTuVM35T0LiiXwlWSQ?usp=sharing
|
|||
|
|
|
|||
|
|
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|||
|
|
import torch
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.3",
|
|||
|
|
device_map="auto",
|
|||
|
|
attn_implementation="flash_attention_2",
|
|||
|
|
torch_dtype=torch.bfloat16)
|
|||
|
|
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.3",use_fast=False)
|
|||
|
|
from transformers import AutoTokenizer, pipeline
|
|||
|
|
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
|||
|
|
prompts = [
|
|||
|
|
"В чем разница между фруктом и овощем?",
|
|||
|
|
"Годы жизни колмагорова?"]
|
|||
|
|
|
|||
|
|
def test_inference(prompt):
|
|||
|
|
prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
|
|||
|
|
print(prompt)
|
|||
|
|
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95, eos_token_id=tokenizer.eos_token_id)
|
|||
|
|
return outputs[0]['generated_text'][len(prompt):].strip()
|
|||
|
|
|
|||
|
|
|
|||
|
|
for prompt in prompts:
|
|||
|
|
print(f" prompt:\n{prompt}")
|
|||
|
|
print(f" response:\n{test_inference(prompt)}")
|
|||
|
|
print("-"*50)
|
|||
|
|
|
|||
|
|
```
|