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
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)
- Downloads last month
- 33
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.