Update README.md

README.md

@@ -13,7 +13,8 @@ GGUF версия: https://huggingface.co/pirbis/Vikhr-7B-instruct_0.2-GGUF
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 import torch
-
+import os
+os.environ['HF_HOME']='.'
 MODEL_NAME = "Vikhrmodels/Vikhr-7B-instruct_0.2"
 DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>\n"
 DEFAULT_SYSTEM_PROMPT = "Ты — Вихрь, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
@@ -55,10 +56,10 @@ def generate(model, tokenizer, prompt, generation_config):
     output_ids = output_ids[len(data["input_ids"][0]):]
     output = tokenizer.decode(output_ids, skip_special_tokens=True)
     return output.strip()
-    
+
 #config = PeftConfig.from_pretrained(MODEL_NAME)
 model = AutoModelForCausalLM.from_pretrained(
-    config.base_model_name_or_path,
+    MODEL_NAME,
     load_in_8bit=True,
     torch_dtype=torch.float16,
     device_map="auto"
@@ -67,7 +68,12 @@ model = AutoModelForCausalLM.from_pretrained(
 model.eval()
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, use_fast=False)
+
 generation_config = GenerationConfig.from_pretrained(MODEL_NAME)
+generation_config.max_length=256
+generation_config.top_p=0.9
+generation_config.top_k=30
+generation_config.do_sample = True
 print(generation_config)
 
 inputs = ["Как тебя зовут?", "Кто такой Колмогоров?"]