updated readme

Browse files

Files changed (1) hide show

README.md +55 -250

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-title: Trek Nepal 3B
 emoji: 🏔️
 colorFrom: blue
 colorTo: green
@@ -29,284 +29,89 @@ license: apache-2.0
 # Trek Nepal 3B - Fine-tuned Llama-3.2-3B for Nepal Trekking
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) specifically trained on Nepal trekking and travel information.
-## Model Details
-- **Base Model**: meta-llama/Llama-3.2-3B-Instruct
-- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
-- **LoRA Rank**: 256
-- **LoRA Alpha**: 512
-- **Specialization**: Nepal trekking routes, permits, gear, weather, safety, accommodation, costs, and preparation
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-- **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]
-### Framework versions
-- PEFT 0.16.0
-## Usage
-### Using with Transformers
 ```python
-from transformers import AutoTokenizer, AutoModelForCausalLM
-from peft import PeftModel
 import torch
-# Load the base model
-base_model = AutoModelForCausalLM.from_pretrained(
-    "Qwen/Qwen2.5-3B",
     torch_dtype=torch.bfloat16,
-    device_map="auto"
 )
-# Load the tokenizer
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B")
-# Load the LoRA adapter
-model = PeftModel.from_pretrained(base_model, "your-username/trek-nepal-3b")
-# Generate text
-prompt = "What permits do I need for Everest Base Camp trek?"
-inputs = tokenizer(prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_length=200, temperature=0.7)
-response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-print(response)
 ```
-### Chat Template
-The model uses the Qwen2.5 chat template format:
-```
-<|im_start|>system
-You are a helpful assistant specialized in providing information about trekking in Nepal.
-<|im_end|>
-<|im_start|>user
-{user_message}
-<|im_end|>
-<|im_start|>assistant
-```
-## Training Details
-- **Training Method**: Supervised Fine-Tuning (SFT) with LoRA
-- **Dataset**: Custom Nepal trekking Q&A dataset
-- **Optimization**: 4-bit quantization with bfloat16
-- **GPU**: Optimized for L40S GPU training
-- **Batch Size**: 16 with gradient accumulation steps of 2
-## Intended Use
-This model is specifically designed for:
-- Nepal trekking route information
-- Permit requirements and procedures
-- Gear and equipment recommendations
-- Weather and seasonal advice
-- Safety guidelines and preparations
-- Accommodation and logistics
-- Cost estimation and budgeting
 ## Limitations
-- Specialized only for Nepal trekking topics
-- May not perform well on general conversation topics
-- Information is based on training data and should be verified with official sources
-- Always consult local authorities and guides for current conditions
 ## License
-This model is licensed under Apache 2.0.
-## Training Configuration
-The model was trained using the following LoRA configuration:
-- **r**: 128
-- **lora_alpha**: 256
-- **lora_dropout**: 0.05
-- **target_modules**: ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]
-- **bias**: "none"
-- **task_type**: "CAUSAL_LM"

 ---
+title: Trek-Nepal-3B
 emoji: 🏔️
 colorFrom: blue
 colorTo: green
 # Trek Nepal 3B - Fine-tuned Llama-3.2-3B for Nepal Trekking
+Trek Nepal 3B is a specialized fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) that focuses exclusively on Nepal trekking information. The model was trained on a comprehensive dataset of mountaineering books, trekker guides, and web-scraped content with approximately 3.8k examples, including 300 negative examples for better response quality.
+**Developed by:** Ashok BK (blazewild)
+## Links
+- 🤗 **Hugging Face**: https://huggingface.co/blazewild/trek-nepal
+- 🦙 **Ollama**: https://ollama.com/blazewild/trek-nepal
+- 📝 **Medium Blog**: [Coming Soon]
+## Quick Start
+### Ollama (Recommended)
+```bash
+ollama run blazewild/trek-nepal
+```
+### Transformers
 ```python
 import torch
+from transformers import pipeline
+model_id = "blazewild/trek-nepal"
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
     torch_dtype=torch.bfloat16,
+    device_map="auto",
 )
+messages = [
+    {"role": "system", "content": "You are Trek Nepal, a friendly and knowledgeable Nepal trekking expert assistant. You specialize in providing information about trekking in Nepal.\n\nYou can respond to greetings, have casual conversations, and be helpful and personable. When it comes to providing information, you focus exclusively on Nepal trekking topics in detail.\n\nFor Nepal trekking questions, provide detailed, comprehensive answers with everything you know about the topic. Use natural formatting with headings, bullet points, and proper structure in markdown format. Write in a conversational yet informative style, adapting very detail level based on the complexity of the question.\n\nFor questions completely unrelated to Nepal trekking, politely redirect: \"I'm sorry, I specialize in Nepal trekking information. Is there anything about trekking in Nepal I can help you with?\"\n\nBe natural, thorough, and conversational while maintaining your expertise in Nepal trekking."},
+    {"role": "user", "content": "What permits do I need for Everest Base Camp trek?"},
+]
+outputs = pipe(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
 ```
+## What it does
+This model specializes in providing expert guidance on Nepal trekking topics:
+- **Trekking Routes**: Detailed information about popular routes like Everest Base Camp, Annapurna Circuit, Langtang Valley, etc.
+- **Permits & Logistics**: Requirements, procedures, and costs for trekking permits
+- **Gear & Equipment**: Recommendations for different seasons and routes
+- **Weather & Safety**: Seasonal advice, safety protocols, and preparation tips
+- **Accommodation & Planning**: Logistics, costs, and itinerary planning
+For questions outside Nepal trekking, it politely redirects users back to its area of expertise.
+## Training Details
+- **Base Model**: meta-llama/Llama-3.2-3B-Instruct
+- **Fine-tuning**: LoRA (Low-Rank Adaptation)
+- **Dataset**: ~3.8k examples from mountaineering books, trekker guides, and web scrapes
+- **Negative Examples**: 300 examples for better refusal behavior
+- **Training Time**: 1 hour on 1x L40S GPU
+### LoRA Configuration
+- **Rank**: 128
+- **Alpha**: 256
+- **Dropout**: 0.05
+- **Epochs**: 10
+- **Batch Size**: 128
 ## Limitations
+- **Domain-Specific**: Only provides information about Nepal trekking
+- **Information Currency**: Based on training data; always verify current conditions
+- **Safety Critical**: Always consult local authorities and guides for current trail conditions
+- **Not Medical Advice**: Consult healthcare professionals for medical concerns
 ## License
+Apache 2.0
+---
+_For questions or issues, please contact through the Hugging Face model repository._