Upload README.md with huggingface_hub

README.md

@@ -12,18 +12,18 @@ tags:
 - technical-analysis
 ---
 
-# 📂 Solvrays Finetuned Pdf - High Precision Document Analyst
+# 📂 Solvrays Finetuned Pdf - Senior Document AI
 
-## 🌟 Overview
-This model is a specialized fine-tuning of **google/gemma-2b-it**, engineered for **Zero-Hallucination Document Retrieval**. It has been optimized to handle complex, domain-specific documents (Technical, Legal, or Architectural) with strict adherence to provided context.
+## 🌟 Model Overview
+This model is a high-precision fine-tuning of **google/gemma-2b-it**, specifically architected for **Zero-Hallucination Technical Retrieval**. It has been trained on a proprietary dataset of technical and architectural documentation to ensure deep contextual grounding.
 
-### 📋 Technical Objectives
-- **Factual Integrity**: Hardcoded propensity to avoid speculation.
-- **Contextual Continuity**: Overlap-aware training prevents information loss across page boundaries.
-- **Domain Versatility**: Seamlessly switches between technical and non-technical document styles.
+### 🚀 Key Capabilities
+- **Technical Grounding**: Prioritizes factual documentation over generative speculation.
+- **Chunk-Aware Memory**: Optimized for overlapping document segments (256-token window).
+- **Deterministic Precision**: Best used with `do_sample=False` for architectural accuracy.
 
 ## 💻 Professional Implementation
-To achieve the trained precision level, utilize the following standardized implementation:
+The model requires specific prompt construction to trigger its 'Knowledge Retrieval' mode:
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -31,34 +31,41 @@ import torch
 
 model_id = 'solvrays/solvrays-finetuned-pdf'
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto', torch_dtype=torch.bfloat16)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    device_map='auto', 
+    torch_dtype=torch.bfloat16, 
+    quantization_config={'load_in_4bit': True}
+)
 
-# Universal Retrieval Template
-query = 'What are the infrastructure requirements?'
-prompt = f'### Knowledge Retrieval Content: {query}
-### Verified Response: '
-
-inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
-with torch.no_grad():
-    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False, repetition_penalty=1.2)
-
-print(tokenizer.decode(outputs[0], skip_special_tokens=True).split('### Verified Response:')[-1].strip())
+def query_model(user_query):
+    # High-Precision Retrieval Template
+    prompt = f'### Knowledge Retrieval Content: {user_query}\n### Verified Response: '
+    inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True).split('### Verified Response:')[-1].strip()
 ```
 
-## 📊 Model Specifications
-| Parameter | Configuration |
+## 📊 Technical Specifications
+| Feature | Configuration |
 | :--- | :--- |
-| Base Model | google/gemma-2b-it |
-| Fine-tuning Method | QLoRA (4-bit quantization) |
-| LoRA Rank (r) | 16 |
-| LoRA Alpha | 32 |
-| Learning Rate | 2e-4 |
-| Training Epochs | 20 |
+| **Base Model** | google/gemma-2b-it |
+| **Precision** | BrainFloat16 (BF16) |
+| **Fine-tuning** | QLoRA (4-bit Normalized Float) |
+| **LoRA Rank (r)** | 16 |
+| **LoRA Alpha** | 32 |
+| **Target Modules** | q, k, v, o, gate, up, down |
+| **Training Epochs** | 25 |
+
+## 🛠 Training Environment
+- **Hardware**: NVIDIA L4 x 2 (Dual GPU Architecture)
+- **Optimizer**: Paged AdamW 8-bit
+- **Context Length**: 256 tokens per block
 
-## ⚠️ Constraints & Compliance
-- **Context Window**: Optimized for 256-512 token blocks. For multi-document search beyond 10+ pages, RAG integration is recommended.
-- **Bias Awareness**: Reflects the factual contents of the provided technical PDFs.
-- **Verification**: Always cross-reference critical numeric values with source documents.
+## ⚠️ Constraints & Risk Mitigation
+- **Out-of-Scope**: This model is not intended for general conversation or creative writing. It is a specialized document analyst.
+- **Hallucination Control**: If information is not present in the internal weights, the model is trained to state 'Not Documented' or provide an empty response for verification.
+- **Numerical Accuracy**: Always cross-verify critical measurements with original PDF source material.
 
 ---
-**Architected and Fine-tuned by Bibek Lama Singtan**
+**Senior AI Architect & Developer**: Bibek Lama Singtan