Update README.md

README.md

@@ -37,36 +37,21 @@ This model is not suitable for direct use outside of research.
 This model should never be used for critical decisions involving health, life, employment, housing, law, etc. It should also never be used to harm anyone.
 
 
+
+
 ## Bias, Risks, and Limitations
 
 [No safegaurd have been added to this model.](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta#bias-risks-and-limitations)
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-'''python
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
-
-model_name = 'kettleguts/zephyr-7b-beta_sparse05'
-
-#quantize model for mode efficient performance
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.bfloat16
-)
+Use the code below to get started with the model:
 
-#load model
-model = AutoModelForCausalLM.from_pretrained(model_name,
-                                             device_map = "auto",
-                                             quantization_config=bnb_config)
+<blockquote>
+    
+```Python
 
-#load toeknizer
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-if tokenizer.pad_token is None:
-    tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+from transformers import pipeline
 
 pipe = pipeline("text-generation",model=model, tokenizer=tokenizer)
 
@@ -75,92 +60,57 @@ messages = [
         "role": "system",
         "content": "You are a friendly chatbot who always responds as briefly as possible with prefect grammar.",
     },
-    {"role": "user", "content": "Briefly describe network pruning."},
-]
+        {"role": "user", "content": "Briefly describe network pruning."},
+    ]
+    
 prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95,pad_token_id = tokenizer.pad_token_id)
+
+outputs = pipe(prompt,
+               max_new_tokens=256,
+               do_sample=True,
+               temperature=0.7,
+               top_k=50,
+               top_p=0.95,
+               pad_token_id = tokenizer.pad_token_id)
+               
 text = str(outputs[0]).split('<|assistant|>\\n')
 print(text[-1])
 
-#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.'}
-'''
-
+```
 
+</blockquote>
 
+Output:
+>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.'}
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
+Pending
 
 
 ## Model Examination [optional]
 
 <!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+Pending
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+The calculations necessary to prune this model required less than 1 hour of time on a T4 GPU in Colab.
 
 ## Technical Specifications [optional]
 
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
 
 #### Software
 
-[More Information Needed]
+The bulk of this work was done using [Pytorch](https://pytorch.org/). They have an array of built-in [pruning tools](https://pytorch.org/docs/stable/nn.html#:~:text=Utility%20classes%20and%20functions%20for%20pruning%20Module%20parameters
+) in torch.nn . Also check out the [tutorial](https://pytorch.org/tutorials/intermediate/pruning_tutorial.html) by [Michela Paganini](https://github.com/mickypaganini).
 
 ## Citation [optional]
 
 **BibTeX:**
-'''
-@misc{tunstall2023zephyr,
+<code>
+
+>@misc{tunstall2023zephyr,
       title={Zephyr: Direct Distillation of LM Alignment}, 
       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},
       year={2023},
@@ -168,9 +118,9 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
       archivePrefix={arXiv},
       primaryClass={cs.LG}
 }
-'''
-'''
-@misc{sun2023simple,
+
+    
+>@misc{sun2023simple,
       title={A Simple and Effective Pruning Approach for Large Language Models}, 
       author={Mingjie Sun and Zhuang Liu and Anna Bair and J. Zico Kolter},
       year={2023},
@@ -178,5 +128,8 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
       archivePrefix={arXiv},
       primaryClass={cs.CL}
 }
-'''
+
+</code>
+
+