Update app.py

app.py

@@ -1,23 +1,32 @@
-# pip install transformers==4.41.1
+import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from huggingface_hub import login
-login()
-
-model_id = "CohereForAI/aya-23-8B"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
-
-# Format message with the command-r-plus chat template
-messages = [{"role": "user", "content": "Расскажи о себе"}]
-input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
-## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
-
-gen_tokens = model.generate(
-    input_ids, 
-    max_new_tokens=100, 
-    do_sample=True, 
-    temperature=0.3,
-    )
-
-gen_text = tokenizer.decode(gen_tokens[0])
-print(gen_text)
+import torch
+
+
+
+
+
+
+model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4",
+                                             device_map="auto",
+                                             attn_implementation="flash_attention_2",
+                                             torch_dtype=torch.bfloat16)
+
+tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
+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)