File size: 1,659 Bytes
75e394f
 
 
 
 
a7da558
 
55da335
 
75e394f
 
f36e29f
75e394f
a87bee4
 
058d7b4
 
f1c41f6
632e2c6
 
 
a87bee4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
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

Метрки, DPO, коды для запуска подьедут позже

используйте transformers==4.36.2 и будет счастье



```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)

```