Update README.md

README.md

@@ -1,3 +1,121 @@
 ---
 license: apache-2.0
 ---
+### BioinspiredMixtral: Large Language Model for the Mechanics of Biological and Bio-Inspired Materials using Mixture-of-Experts
+
+To accelerate discovery and guide insights, we report an open-source autoregressive transformer large language model (LLM), trained on expert knowledge in the biological materials field, especially focused on mechanics and structural properties.
+
+The model is finetuned with a corpus of over a thousand peer-reviewed articles in the field of structural biological and bio-inspired materials and can be prompted to recall information, assist with research tasks, and function as an engine for creativity. 
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/K0GifLVENb8G0nERQAzeQ.png)
+
+This model is based on work reported in https://doi.org/10.1002/advs.202306724, but focused on the development of a mixture-of-experts strategy. 
+
+The model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1. 
+
+```
+from llama_cpp import Llama
+
+model_path='lamm-mit/BioinspiredMixtral/ggml-model-q5_K_M.gguf'
+chat_format="mistral-instruct"
+
+llm = Llama(model_path=model_path,
+            n_gpu_layers=-1,verbose= True, 
+            n_ctx=10000,
+            #main_gpu=0,
+            chat_format=chat_format,
+            #split_mode=llama_cpp.LLAMA_SPLIT_LAYER
+            )
+```
+
+Or, download directly from Hugging Face:
+
+```
+from llama_cpp import Llama
+
+model_path='lamm-mit/BioinspiredMixtral/ggml-model-q5_K_M.gguf'
+chat_format="mistral-instruct"
+
+llm = Llama.from_pretrained(
+    repo_id=model_path,
+    filename="*q5_K_M.gguf",
+    verbose=True,
+    n_gpu_layers=-1, 
+    n_ctx=10000,
+    #main_gpu=0,
+    chat_format=chat_format,
+)
+```
+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
+
+    if system_prompt==None:
+        messages=[ 
+            {"role": "user", "content": prompt},
+            ]
+    else:
+        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]
+
+start_time = time.time()
+result=generate_BioMixtral(system_prompt='You respond accurately.', 
+                        prompt="What is graphene? Answer with detail.",
+                        max_tokens=512, temperature=0.7,  )
+
+print (result)
+deltat=time.time() - start_time
+print("--- %s seconds ---" % deltat)
+toked=tokenizer(res)
+print ("Tokens per second (generation): ", len (toked['input_ids'])/deltat)
+```