Ayush2312
/

llama2-7B-orca-colab

@@ -1,201 +1,86 @@
----
-library_name: transformers
-tags: []
----
-# 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]

+Fine-tuned llama 2 7b with processed open orca dataset (Ayush2312/deduplicated_orca_post_processed):
+data processing:
+1. Remove output token less than 100 tokens in reponse
+2. Do cosine similarity on examples with threshold 0.95
+3.
+python codes for data processing:
+step 1:
+```
+from datasets import load_dataset, Dataset
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+# Load your dataset from Hugging Face
+dataset = load_dataset("Ayush2312/orca-1m-gpt4", split='train[:7000]')
+# Tokenize your text data
+texts = dataset['system_prompt'] + dataset['question'] + dataset['response']
+# Filter out instructions with less than 100 tokens in response
+filtered_texts = []
+for i, response in enumerate(dataset['response']):
+    if len(response.split()) >= 100:
+        filtered_texts.append({'system_prompt': dataset['system_prompt'][i],
+                               'question': dataset['question'][i],
+                               'response': response})
+# TF-IDF Vectorization for deduplication
+texts = [text['system_prompt'] + ' ' + text['question'] + ' ' + text['response'] for text in filtered_texts]
+vectorizer = TfidfVectorizer()
+tfidf_matrix = vectorizer.fit_transform(texts)
+# Calculate cosine similarity for deduplication
+cos_sim_matrix = cosine_similarity(tfidf_matrix, tfidf_matrix)
+# Deduplicate the data based on cosine similarity
+deduplicated_indices = set()
+for i in range(len(cos_sim_matrix)):
+    if i not in deduplicated_indices:
+        for j in range(i + 1, len(cos_sim_matrix)):
+            if cos_sim_matrix[i, j] > 0.95:
+                deduplicated_indices.add(j)
+# Create a new dataset with the deduplicated data
+deduplicated_texts = [filtered_texts[i] for i in range(len(filtered_texts)) if i not in deduplicated_indices]
+deduplicated_texts_dict = {key: [item[key] for item in deduplicated_texts] for key in filtered_texts[0].keys()}
+deduplicated_dataset = Dataset.from_dict(deduplicated_texts_dict)
+# Publish the dataset on Hugging Face
+deduplicated_dataset.push_to_hub("deduplicated_orca_processed")
+```
+step 2:
+```
+from datasets import Dataset, load_dataset
+# Load your Hugging Face dataset
+dataset = load_dataset("Ayush2312/deduplicated_orca_processed")['train'][:1000]
+# Define the default instruction
+default_instruction = "### Instruction: Below is a conversation between a human and an AI agent. Write a summary of the conversation."
+# Define the function to format each example
+def format_example(example):
+    input_text = "### Input:\n"
+    if "response" in example:
+        input_text += "\n".join([f" {example[role]}" for role in ["question"]])
+    else:
+        input_text += "\n".join([f" {example[role]}" for role in ["question"]])
+    response_text = example["response"] if "response" in example else ""
+    instruction = "### Instruction: " + example["system_prompt"]
+    if not example["system_prompt"].strip():
+        instruction = default_instruction  # Fill empty or missing instruction with default
+    return {
+        "formatted_example": f"{instruction}\n\n{input_text}\n\n### Response:\n{response_text}"
+    }
+# Convert the dictionary to a Dataset object
+dataset = Dataset.from_dict(dataset)
+# Apply the function to format each example
+formatted_dataset = dataset.map(format_example)
+# Upload the new dataset to Hugging Face
+formatted_dataset.push_to_hub("deduplicated_orca_post_processed")
+```