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 - GGUF
- Model creator: https://huggingface.co/Vikhrmodels/
- Original model: https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.4/
Name | Quant method | Size |
---|---|---|
Vikhr-7B-instruct_0.4.Q2_K.gguf | Q2_K | 2.74GB |
Vikhr-7B-instruct_0.4.IQ3_XS.gguf | IQ3_XS | 3.04GB |
Vikhr-7B-instruct_0.4.IQ3_S.gguf | IQ3_S | 3.19GB |
Vikhr-7B-instruct_0.4.Q3_K_S.gguf | Q3_K_S | 3.17GB |
Vikhr-7B-instruct_0.4.IQ3_M.gguf | IQ3_M | 3.29GB |
Vikhr-7B-instruct_0.4.Q3_K.gguf | Q3_K | 3.5GB |
Vikhr-7B-instruct_0.4.Q3_K_M.gguf | Q3_K_M | 3.5GB |
Vikhr-7B-instruct_0.4.Q3_K_L.gguf | Q3_K_L | 3.79GB |
Vikhr-7B-instruct_0.4.IQ4_XS.gguf | IQ4_XS | 3.92GB |
Vikhr-7B-instruct_0.4.Q4_0.gguf | Q4_0 | 4.08GB |
Vikhr-7B-instruct_0.4.IQ4_NL.gguf | IQ4_NL | 4.12GB |
Vikhr-7B-instruct_0.4.Q4_K_S.gguf | Q4_K_S | 4.11GB |
Vikhr-7B-instruct_0.4.Q4_K.gguf | Q4_K | 4.32GB |
Vikhr-7B-instruct_0.4.Q4_K_M.gguf | Q4_K_M | 4.32GB |
Vikhr-7B-instruct_0.4.Q4_1.gguf | Q4_1 | 4.5GB |
Vikhr-7B-instruct_0.4.Q5_0.gguf | Q5_0 | 4.93GB |
Vikhr-7B-instruct_0.4.Q5_K_S.gguf | Q5_K_S | 4.93GB |
Vikhr-7B-instruct_0.4.Q5_K.gguf | Q5_K | 5.05GB |
Vikhr-7B-instruct_0.4.Q5_K_M.gguf | Q5_K_M | 5.05GB |
Vikhr-7B-instruct_0.4.Q5_1.gguf | Q5_1 | 5.35GB |
Vikhr-7B-instruct_0.4.Q6_K.gguf | Q6_K | 5.83GB |
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
- 69
Unable to determine this model's library. Check the
docs
.