mjbuehler commited on
Commit
7bcef9f
·
verified ·
1 Parent(s): 7fbe908

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -7,11 +7,11 @@ To accelerate discovery and guide insights, we report an open-source autoregress
7
 
8
  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.
9
 
10
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/K0GifLVENb8G0nERQAzeQ.png)
11
 
12
- 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.
13
 
14
- The model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1.
15
 
16
  ```
17
  from llama_cpp import Llama
@@ -73,7 +73,6 @@ start_time = time.time()
73
  result=generate_BioMixtral(system_prompt='You respond accurately.',
74
  prompt="What is graphene? Answer with detail.",
75
  max_tokens=512, temperature=0.7, )
76
-
77
  print (result)
78
  deltat=time.time() - start_time
79
  print("--- %s seconds ---" % deltat)
 
7
 
8
  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.
9
 
10
+ The model is based on mistralai/Mixtral-8x7B-Instruct-v0.1.
11
 
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/K0GifLVENb8G0nERQAzeQ.png)
13
 
14
+ This model is based on work reported in https://doi.org/10.1002/advs.202306724, but uses a mixture-of-experts strategy.
15
 
16
  ```
17
  from llama_cpp import Llama
 
73
  result=generate_BioMixtral(system_prompt='You respond accurately.',
74
  prompt="What is graphene? Answer with detail.",
75
  max_tokens=512, temperature=0.7, )
 
76
  print (result)
77
  deltat=time.time() - start_time
78
  print("--- %s seconds ---" % deltat)