YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Vikhr-7B-instruct_0.4 - bnb 4bits
- Model creator: https://huggingface.co/Vikhrmodels/
- Original model: https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.4/
Original model description:
library_name: transformers tags: []
Релиз вихря 0.3-0.4
Долили сильно больше данных в sft, теперь стабильнее работает json и multiturn, слегка подточили параметры претрена модели
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model = AutoModelForCausalLM.from_pretrained("AlexWortega/v5-it",
device_map="auto",
attn_implementation="flash_attention_2",
torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("AlexWortega/v5-it")
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=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
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
- 16