Update README.md

README.md

@@ -48,65 +48,26 @@ llm = Llama.from_pretrained(
 ```
 For inference:
 ```
-def generate_response (model,tokenizer,text_input="Biology offers amazing possibilities, especially for",
-                      num_return_sequences=1,
-                      temperature=1., #the higher the temperature, the more creative the model becomes
-                      max_new_tokens=127,
-                      num_beams=1,
-                      top_k = 50,
-                      top_p =0.9,repetition_penalty=1.,eos_token_id=2,verbatim=False,
-                      exponential_decay_length_penalty_fac=None,add_special_tokens  =True,  
-                      ):
-    inputs = tokenizer(text_input, add_special_tokens = add_special_tokens, return_tensors ='pt').to(device)
-
-    with torch.no_grad():
-         
-          outputs = model.generate (input_ids = inputs["input_ids"],
-                                    attention_mask = inputs["attention_mask"] , # This is usually done automatically by the tokenizer
-                                    max_new_tokens=max_new_tokens,
-                                    temperature=temperature, #value used to modulate the next token probabilities.
-                                    num_beams=num_beams,
-                                    top_k = top_k,
-                                    top_p = top_p,
-                                    num_return_sequences = num_return_sequences,
-                                    eos_token_id=eos_token_id,
-                                    pad_token_id = eos_token_id,
-                                    do_sample =True,#skip_prompt=True,
-                                    repetition_penalty=repetition_penalty,
-                                   )
-
-    return tokenizer.batch_decode(outputs[:,inputs["input_ids"].shape[1]:].detach().cpu().numpy(), skip_special_tokens=True)
-
-def generate_BioMixtral  (system_prompt='You a helpful assistant. You are familiar with materials science, especially biological and bioinspired materials. ',
-                          prompt='What is spider silk in the context of bioinspired materials?',
-                          repetition_penalty=1.,
-                          top_p=0.9, top_k=256,  
-                          temperature=0.5, max_tokens=512, verbatim=False, eos_token=None,
-                          prepend_response='',
-                         ):
-
-    if eos_token==None:
-        eos_token= tokenizer.eos_token_id
+def generate_BioMixtral (system_prompt='You are an expert in biological materials, mechanics and related topics.', prompt="What is spider silk?",
+             temperature=0.0,
+             max_tokens=10000,  
+             ):
 
     if system_prompt==None:
-        messages=[ 
+        messages=[
             {"role": "user", "content": prompt},
             ]
     else:
-        messages=[ 
-        {"role": "system", "content": system_prompt},
-        {"role": "user", "content": prompt},
+        messages=[
+            {"role": "system",  "content": system_prompt},
+            {"role": "user", "content": prompt},
         ]
-    txt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True,
-                                        )
-    txt=txt+prepend_response
-     
-    output_text=generate_response (model,tokenizer,text_input=txt,eos_token_id=eos_token,
-                                   num_return_sequences=1,  repetition_penalty=repetition_penalty,
-                                   top_p=top_p, top_k=top_k,  
-                                   temperature=temperature,max_new_tokens=max_tokens, verbatim=verbatim, 
-                                  )
-    return output_text[0]
+
+    result=llm.create_chat_completion(
+            messages=messages,
+            temperature=temperature,
+            max_tokens=max_tokens,
+        )
 
 start_time = time.time()
 result=generate_BioMixtral(system_prompt='You respond accurately.',