Text Generation
Transformers
Safetensors
English
mistral
sparse
pruned
wanda
conversational
text-generation-inference
kettleguts commited on
Commit
a581c28
·
verified ·
1 Parent(s): 7563713

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -45,7 +45,7 @@ This model should never be used for critical decisions involving health, life, e
45
 
46
  Use the code below to get started with the model.
47
 
48
- <code>
49
  from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
50
 
51
  model_name = 'kettleguts/zephyr-7b-beta_sparse05'
@@ -83,7 +83,7 @@ text = str(outputs[0]).split('<|assistant|>\\n')
83
  print(text[-1])
84
 
85
  #Network pruning, in the context of artificial intelligence and machine learning, refers to the process of removing unimportant or redundant connections, or "pruning," from a neural network\'s architecture. This is done to simplify and optimize the network\'s structure, reduce overfitting, and improve its efficiency, while preserving its overall performance. Pruning typically involves removing connections, neurons, or entire layers, based on metrics such as the weight or sparsity of the connection, or the amount of improvement gained by removing the connection. The goal is to prune the network in a way that balances the trade-off between model size and accuracy, while reducing the network\'s overall complexity and resource requirements. Pruning techniques can range from simple heuristics such as early stopping, to more sophisticated methods such as compressed and pruned models, and iterative and incremental pruning.'}
86
- </code>
87
 
88
 
89
 
@@ -159,7 +159,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
159
  ## Citation [optional]
160
 
161
  **BibTeX:**
162
-
163
  @misc{tunstall2023zephyr,
164
  title={Zephyr: Direct Distillation of LM Alignment},
165
  author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
@@ -168,7 +168,8 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
168
  archivePrefix={arXiv},
169
  primaryClass={cs.LG}
170
  }
171
-
 
172
  @misc{sun2023simple,
173
  title={A Simple and Effective Pruning Approach for Large Language Models},
174
  author={Mingjie Sun and Zhuang Liu and Anna Bair and J. Zico Kolter},
@@ -177,5 +178,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
177
  archivePrefix={arXiv},
178
  primaryClass={cs.CL}
179
  }
180
-
181
 
 
45
 
46
  Use the code below to get started with the model.
47
 
48
+ '''python
49
  from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
50
 
51
  model_name = 'kettleguts/zephyr-7b-beta_sparse05'
 
83
  print(text[-1])
84
 
85
  #Network pruning, in the context of artificial intelligence and machine learning, refers to the process of removing unimportant or redundant connections, or "pruning," from a neural network\'s architecture. This is done to simplify and optimize the network\'s structure, reduce overfitting, and improve its efficiency, while preserving its overall performance. Pruning typically involves removing connections, neurons, or entire layers, based on metrics such as the weight or sparsity of the connection, or the amount of improvement gained by removing the connection. The goal is to prune the network in a way that balances the trade-off between model size and accuracy, while reducing the network\'s overall complexity and resource requirements. Pruning techniques can range from simple heuristics such as early stopping, to more sophisticated methods such as compressed and pruned models, and iterative and incremental pruning.'}
86
+ '''
87
 
88
 
89
 
 
159
  ## Citation [optional]
160
 
161
  **BibTeX:**
162
+ '''
163
  @misc{tunstall2023zephyr,
164
  title={Zephyr: Direct Distillation of LM Alignment},
165
  author={Lewis Tunstall and Edward Beeching and Nathan Lambert and Nazneen Rajani and Kashif Rasul and Younes Belkada and Shengyi Huang and Leandro von Werra and Clémentine Fourrier and Nathan Habib and Nathan Sarrazin and Omar Sanseviero and Alexander M. Rush and Thomas Wolf},
 
168
  archivePrefix={arXiv},
169
  primaryClass={cs.LG}
170
  }
171
+ '''
172
+ '''
173
  @misc{sun2023simple,
174
  title={A Simple and Effective Pruning Approach for Large Language Models},
175
  author={Mingjie Sun and Zhuang Liu and Anna Bair and J. Zico Kolter},
 
178
  archivePrefix={arXiv},
179
  primaryClass={cs.CL}
180
  }
181
+ '''
182