update-README

README.md

@@ -1,11 +1,17 @@
 ---
 library_name: transformers
-tags: []
+license: apache-2.0
+datasets:
+- yahma/alpaca-cleaned
+language:
+- en
+base_model:
+- NousResearch/Hermes-2-Pro-Mistral-7B
 ---
 
-# Model Card for Model ID
+# 📘 Model Card for askmydocs-lora-v1
 
-<!-- Provide a quick summary of what the model is/does. -->
+This model card provides detailed information about askmydocs-lora-v1, a fine-tuned conversational AI model.
 
 
 
@@ -13,187 +19,175 @@ tags: []
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+askmydocs-lora-v1 is a lightweight and efficient instruction-tuned conversational AI model derived from Hermes-2-Pro-Mistral-7b, optimized using Low-Rank Adaptation (LoRA). It was fine-tuned with the yahma/alpaca-cleaned dataset, specifically a curated subset of 10,000 samples, to enhance performance in retrieval and conversational interactions.
 
-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: deanngkl
 
-- **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 Type: Instruction-tuned conversational AI (LLM)
 
-### Model Sources [optional]
+- Languages: English (primarily)
+
+- License: Apache-2.0
+
+- Fine-tuned from model: Hermes-2-Pro-Mistral-7b
+
+### Model Sources 
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [Hugging Face Repository](https://huggingface.co/deanngkl/askmydocs-lora-v1)
 
 ## 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. -->
+- Conversational AI for general queries
+
+- Retrieval-Augmented Generation (RAG) tasks
 
-[More Information Needed]
+- Document summarization and information extraction
 
-### Downstream Use [optional]
+### Downstream Use
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+- Integration into conversational AI platforms
+
+- Customized document analysis systems
+
+- Enhanced customer support solutions
 
-[More Information Needed]
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+- Critical decision-making in healthcare, finance, or legal matters without thorough human review
 
-[More Information Needed]
+- Non-English linguistic applications
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+- May reflect biases present in training data (yahma/alpaca-cleaned)
+
+- Limited effectiveness in domains outside the training scope or highly specialized subjects
 
-[More Information Needed]
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- Users should carefully assess the model outputs for bias and accuracy, especially when deploying in sensitive contexts.
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+- External validation is recommended for critical applications.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("deanngkl/askmydocs-lora-v1")
+model = AutoModelForCausalLM.from_pretrained(
+    "deanngkl/askmydocs-lora-v1",
+    load_in_4bit=True,
+    device_map="auto"
+)
 
-[More Information Needed]
+chat = pipeline("text-generation", model=model, tokenizer=tokenizer)
+response = chat("📄 Document content here\n\nQ: Summarize the document.")
+print(response[0]['generated_text'])
+```
 
 ## 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. -->
+- Dataset: yahma/alpaca-cleaned (10,000 samples)
 
-[More Information Needed]
+- Preprocessing: Standardized prompts, deduplication, profanity and bias filtering
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+- Method: LoRA (Low-Rank Adaptation)
 
-#### Preprocessing [optional]
+- Epochs: 3
 
-[More Information Needed]
+- Batch Size: 4 (gradient accumulation steps: 4)
 
+- Learning Rate: 1e-4
 
-#### Training Hyperparameters
+- Optimizer: AdamW with cosine decay and warm-up
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+- Precision: Mixed (fp16)
 
-#### Speeds, Sizes, Times [optional]
+- Hardware: RunPod Cloud with NVIDIA RTX A5000 GPU (24 GB VRAM)
 
-<!-- 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
+#### Speeds, Sizes, Times
 
-#### Testing Data
+- Checkpoint Size: ~100 MB (LoRA adapters)
 
-<!-- This should link to a Dataset Card if possible. -->
+- Training Duration: Approximately 3 hours
 
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+## Evaluation
 
-[More Information Needed]
+### Testing Data, Factors & Metrics
 
-#### Metrics
+- [Tensorboard Log](https://huggingface.co/deanngkl/askmydocs-lora-v1/tensorboard)
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+- Testing Data: Validation subset (5% of the training set)
 
-[More Information Needed]
+- Metrics: Loss reduction, coherence, instruction-following accuracy
 
 ### Results
 
-[More Information Needed]
+- Validation Loss: Decreased consistently, indicating stable training
 
-#### Summary
+- Instruction-following: Improved coherence and context-awareness
 
+## Environmental Impact
 
+Carbon emissions were minimized by using efficient LoRA fine-tuning on cloud infrastructure:
 
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
+- Hardware Type: NVIDIA RTX A5000
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+- Cloud Provider: RunPod
 
-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).
+- Compute Region: US (West Coast)
 
-- **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]
+- Estimated Carbon Emissions: Low (due to efficient GPU usage and short training duration)
 
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+- Architecture: Hermes-2-Pro-Mistral-7b with LoRA adapters
 
-### Compute Infrastructure
+- Objective: Enhanced conversational abilities for retrieval and instructional tasks
 
-[More Information Needed]
+### Compute Infrastructure
 
 #### Hardware
 
-[More Information Needed]
+Hardware: NVIDIA RTX A5000 (24 GB VRAM)
 
 #### 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]
+Software: Hugging Face Transformers, PyTorch, BitsAndBytes
 
-## More Information [optional]
+## Citation
 
-[More Information Needed]
+```citation
+@misc{deanngkl_askmydocs_lora_v1_2025,
+  title = {askmydocs-lora-v1: Instruction-tuned Hermes-2-Pro-Mistral-7B via LoRA},
+  author = {deanngkl},
+  year = {2025},
+  howpublished = {\url{https://huggingface.co/deanngkl/askmydocs-lora-v1}}
+}
+```
 
-## Model Card Authors [optional]
+## Model Card Authors
 
-[More Information Needed]
+**Dean Ng Kwan Lung**
 
 ## Model Card Contact
 
-[More Information Needed]
+Blog : [Portfolio](https://kwanlung.github.io/)  
+LinkedIn : [LinkedIn](https://www.linkedin.com/in/deanng00/)  
+GitHub : [GitHub](https://github.com/kwanlung)  
+Email : [email protected]