mohamedemam
/

Em2-Mistral-7b

@@ -1,198 +1,171 @@
----
-library_name: peft
----
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## 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
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
 [More Information Needed]
-## 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]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

+language:
+  - en
+license: gpl
+tags:
+  - autograding
+  - essay quetion
+  - sentence similarity
+metrics:
+  - accuracy
+library_name: peft
+datasets:
+  - mohamedemam/Essay-quetions-auto-grading
+Model Card for Model ID
+Model Details
+Model Description
+We are thrilled to introduce our graduation project, the EM5 model, designed for automated essay grading in both Arabic and English. 📝✨
+To develop this model, we first created a custom dataset for training. We adapted the QuAC and OpenOrca datasets to make them suitable for our automated essay grading application.
+Our model utilizes the following impressive models:
+Mistral: 96% LLaMA: 93% FLAN-T5: 93% BLOOMZ (Arabic): 86% MT0 (Arabic): 84%
+You can try our models for auto-grading on Hugging Face! 🌐
+We then deployed these models for practical use. We are proud of our team's hard work and the potential impact of the EM2 model in the field of education. 🌟
+#MachineLearning #AI #Education #EssayGrading #GraduationProject
+    Developed by: mohamed emam
+    Model type: decoder only
+    Language(s) (NLP): English
+    License: gpl
+    Finetuned from model : llama
+    Repository: https://github.com/mohamed-em2m/auto-grading
+Direct Use
+auto grading for essay quetions
+Downstream Use [optional]
+Text generation
 [More Information Needed]
+Training Data
+    mohamedemam/Essay-quetions-auto-grading-arabic
+Training Procedure
+using Trl
+Pipline
+from transformers import Pipeline
+import torch.nn.functional as F
+class MyPipeline:
+    def __init__(self,model,tokenizer):
+        self.model=model
+        self.tokenizer=tokenizer
+    def chat_Format(self,context, quetion, answer):
+                        return "Instruction:/n check answer is true or false of next quetion using context below:\n" + "#context: " + context + f".\n#quetion: " + quetion + f".\n#student answer: " + answer + ".\n#response:"
+    def __call__(self, context, quetion, answer,generate=1,max_new_tokens=4, num_beams=2, do_sample=False,num_return_sequences=1):
+                inp=self.chat_Format(context, quetion, answer)
+                w = self.tokenizer(inp, add_special_tokens=True,
+                                      pad_to_max_length=True,
+                                      return_attention_mask=True,
+                                      return_tensors='pt')
+                response=""
+                if(generate):
+                    outputs = self.tokenizer.batch_decode(self.model.generate(input_ids=w['input_ids'].cuda(), attention_mask=w['attention_mask'].cuda(), max_new_tokens=max_new_tokens, num_beams=num_beams, do_sample=do_sample, num_return_sequences=num_return_sequences), skip_special_tokens=True)
+                    response = outputs
+                s =self.model(input_ids=w['input_ids'].cuda(), attention_mask=w['attention_mask'].cuda())['logits'][0][-1]
+                s = F.softmax(s, dim=-1)
+                yes_token_id = self.tokenizer.convert_tokens_to_ids(self.tokenizer.tokenize("True")[0])
+                no_token_id = self.tokenizer.convert_tokens_to_ids(self.tokenizer.tokenize("False")[0])
+                for i in  ["Yes", "yes", "True", "true","صحيح"]:
+                  for word in self.tokenizer.tokenize(i):
+                    s[yes_token_id] += s[self.tokenizer.convert_tokens_to_ids(word)]
+                for i in ["No", "no", "False", "false","خطأ"]:
+                  for word in self.tokenizer.tokenize(i):
+                    s[no_token_id] += s[self.tokenizer.convert_tokens_to_ids(word)]
+                true = (s[yes_token_id] / (s[no_token_id] + s[yes_token_id])).item()
+                return {"response": response, "true": true}
+context="""Large language models, such as GPT-4, are trained on vast amounts of text data to understand and generate human-like text. The deployment of these models involves several steps:
+    Model Selection: Choosing a pre-trained model that fits the application's needs.
+    Infrastructure Setup: Setting up the necessary hardware and software infrastructure to run the model efficiently, including cloud services, GPUs, and necessary libraries.
+    Integration: Integrating the model into an application, which can involve setting up APIs or embedding the model directly into the software.
+    Optimization: Fine-tuning the model for specific tasks or domains and optimizing it for performance and cost-efficiency.
+    Monitoring and Maintenance: Ensuring the model performs well over time, monitoring for biases, and updating the model as needed."""
+quetion="What are the key considerations when choosing a cloud service provider for deploying a large language model like GPT-4?"
+answer="""When choosing a cloud service provider for deploying a large language model like GPT-4, the key considerations include:
+    Compute Power: Ensure the provider offers high-performance GPUs or TPUs capable of handling the computational requirements of the model.
+    Scalability: The ability to scale resources up or down based on the application's demand to handle varying workloads efficiently.
+    Cost: Analyze the pricing models to understand the costs associated with compute time, storage, data transfer, and any other services.
+    Integration and Support: Availability of tools and libraries that support easy integration of the model into your applications, along with robust technical support and documentation.
+    Security and Compliance: Ensure the provider adheres to industry standards for security and compliance, protecting sensitive data and maintaining privacy.
+    Latency and Availability: Consider the geographical distribution of data centers to ensure low latency and high availability for your end-users.
+By evaluating these factors, you can select a cloud service provider that aligns with your deployment needs, ensuring efficient and cost-effective operation of your large language model."""
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
+config = PeftConfig.from_pretrained("mohamedemam/Em2-llama-7b")
+base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-hf")
+model = PeftModel.from_pretrained(base_model, "mohamedemam/Em2-llama-7b")
+pipe=MyPipeline(model,tokenizer)
+print(pipe(context,quetion,answer,generate=True,max_new_tokens=4, num_beams=2, do_sample=False,num_return_sequences=1))
+    output:{'response': ["Instruction:/n check answer is true or false of next quetion using context below:\n#context: Large language models, such as GPT-4, are trained on vast amounts of text data to understand and generate human-like text. The deployment of these models involves several steps:\n\n Model Selection: Choosing a pre-trained model that fits the application's needs.\n Infrastructure Setup: Setting up the necessary hardware and software infrastructure to run the model efficiently, including cloud services, GPUs, and necessary libraries.\n Integration: Integrating the model into an application, which can involve setting up APIs or embedding the model directly into the software.\n Optimization: Fine-tuning the model for specific tasks or domains and optimizing it for performance and cost-efficiency.\n Monitoring and Maintenance: Ensuring the model performs well over time, monitoring for biases, and updating the model as needed..\n#quetion: What are the key considerations when choosing a cloud service provider for deploying a large language model like GPT-4?.\n#student answer: When choosing a cloud service provider for deploying a large language model like GPT-4, the key considerations include:\n Compute Power: Ensure the provider offers high-performance GPUs or TPUs capable of handling the computational requirements of the model.\n Scalability: The ability to scale resources up or down based on the application's demand to handle varying workloads efficiently.\n Cost: Analyze the pricing models to understand the costs associated with compute time, storage, data transfer, and any other services.\n Integration and Support: Availability of tools and libraries that support easy integration of the model into your applications, along with robust technical support and documentation.\n Security and Compliance: Ensure the provider adheres to industry standards for security and compliance, protecting sensitive data and maintaining privacy.\n Latency and Availability: Consider the geographical distribution of data centers to ensure low latency and high availability for your end-users.\n\nBy evaluating these factors, you can select a cloud service provider that aligns with your deployment needs, ensuring efficient and cost-effective operation of your large language model..\n#response: true the answer is"], 'true': 0.943033754825592}
+Chat Format Function
+This function formats the input context, question, and answer into a specific structure for the model to process.
+def chat_Format(self, context, question, answer):
+    return "Instruction:/n check answer is true or false of next question using context below:\n" + "#context: " + context + f".\n#question: " + question + f".\n#student answer: " + answer + ".\n#response:"
+Configuration
+Dropout Probability for LoRA Layers
+    lora_dropout: 0.05
+Quantization Settings
+    use_4bit: True
+    bnb_4bit_compute_dtype: "float16"
+    bnb_4bit_quant_type: "nf4"
+    use_nested_quant: False
+Output Directory
+    output_dir: "./results"
+Training Parameters
+    num_train_epochs: 1
+    fp16: False
+    bf16: False
+    per_device_train_batch_size: 1
+    per_device_eval_batch_size: 4
+    gradient_accumulation_steps: 8
+    gradient_checkpointing: True
+    max_grad_norm: 0.3
+    learning_rate: 5e-5
+    weight_decay: 0.001
+    optim: "paged_adamw_8bit"
+    lr_scheduler_type: "constant"
+    max_steps: -1
+    warmup_ratio: 0.03
+    group_by_length: True
+Logging and Saving
+    save_steps: 100
+    logging_steps: 25
+    max_seq_length: False