Update JurisGPT — fixed datasets, improved RAG pipeline

README.md

@@ -1,74 +1,16 @@
 ---
-language:
-  - en
-  - hi
-tags:
-  - legal
-  - indian-law
-  - rag
-  - question-answering
-  - classification
-  - legal-bert
+language: [en, hi]
+tags: [legal, indian-law, rag, question-answering]
 license: apache-2.0
-datasets:
-  - nlp4all/indian-constitution
-  - law-ai/ipc-sections
-  - lex_glue
-  - nguha/legalbench
 base_model: Qwen/Qwen2-7B-Instruct
 ---
-
-# ⚖️ JurisGPT — Indian Legal AI Assistant
-
-An AI-powered Indian legal assistant built with **RAG + LegalBERT + Qwen2-7B**.
-
-## 🚀 Capabilities
-- Answer questions about Indian Constitution, IPC sections, and case law
-- Predict case outcomes using LegalBERT classifier
-- Analyze uploaded legal PDF documents
-- Retrieve relevant laws using FAISS semantic search
-- Support for Hindi and regional Indian languages
-
-## 🤖 Architecture
-| Component | Model |
-|-----------|-------|
-| Main LLM | Qwen2-7B-Instruct (4-bit quantized) |
-| Embeddings | BAAI/bge-large-en |
-| Classifier | LegalBERT |
-| Vector DB | FAISS |
-
-## 📚 Legal Corpus (2000 documents)
-- Indian Constitution (`nlp4all/indian-constitution`)
-- IPC Sections (`law-ai/ipc-sections`)
-- LexGLUE Case Law (`lex_glue`)
-- LegalBench (`nguha/legalbench`)
-- Indian Court Judgments
-
-## 💻 Usage
-
+# ⚖️ JurisGPT — Indian Legal AI
+Built with Qwen2-7B + LegalBERT + FAISS RAG on 5027 legal documents.
+## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-
 tokenizer = AutoTokenizer.from_pretrained("Premchan369/JurisGPT")
 model     = AutoModelForCausalLM.from_pretrained("Premchan369/JurisGPT")
-
-messages = [
-    {"role": "system", "content": "You are JurisGPT, an expert Indian legal AI assistant."},
-    {"role": "user",   "content": "Explain IPC Section 302"}
-]
-text   = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(text, return_tensors="pt")
-output = model.generate(**inputs, max_new_tokens=512)
-print(tokenizer.decode(output[0], skip_special_tokens=True))
 ```
-
-## ⚠️ Disclaimer
-JurisGPT provides general legal information for educational purposes only.
-Always consult a qualified lawyer for serious legal matters.
-
-## 🏗️ Built With
-- [Hugging Face Transformers](https://huggingface.co/docs/transformers)
-- [FAISS](https://faiss.ai/)
-- [Sentence Transformers](https://www.sbert.net/)
-- [Gradio](https://gradio.app/)
-- [Kaggle](https://www.kaggle.com/)
+## Disclaimer
+For informational purposes only. Not a substitute for professional legal advice.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -1,52 +1,21 @@
 {
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "dtype": "bfloat16",
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 18944,
-  "layer_types": [
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention",
-    "full_attention"
-  ],
   "max_position_embeddings": 32768,
   "max_window_layers": 28,
   "model_type": "qwen2",
   "num_attention_heads": 28,
   "num_hidden_layers": 28,
   "num_key_value_heads": 4,
-  "pad_token_id": null,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -63,13 +32,11 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,
-  "rope_parameters": {
-    "rope_theta": 1000000.0,
-    "rope_type": "default"
-  },
+  "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "5.2.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 152064

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "5.2.0"
+  "transformers_version": "4.44.0"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aaa99d9d11209d9e7218e9d775872219f99d3f0e97f332df6cdb581ea01151
+size 4457259454

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b6eef54ae6fe69f5715367e066a3f8a1c6d233fed8feb5bb358bf107d54660
+size 1089994880

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
-size 11418262
+oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1
+size 7028043

tokenizer_config.json

@@ -1,15 +1,40 @@
 {
   "add_prefix_space": false,
-  "backend": "tokenizers",
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
   "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "is_local": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,