Update README.md

README.md

@@ -10,6 +10,102 @@ language:
 - en
 ---
 
+
+The model was finetuned on ~128,000 curated transcripts across different domanins and language preferences
+- Expanded Training: Now optimized for CX Support, Healthcare, Loan Collection, Insurance, Ecommerce, and Concierge services.
+- Feature Improvement: Significantly enhanced relative date-time extraction for more precise data processing.
+- Training Overview
+  - You can plug it into your calling or voice AI stack to automatically extract:
+    - Enum-based classifications (e.g., call outcome, intent, disposition)
+    - Conversation summaries
+    - Action items / follow-ups
+    - Relative DateTime Artifacts
+
+It’s built to handle real-world Hindi, English, Indic noisy transcripts.
+
+Finetuning Parameters:
+```
+rank = 64 # kept small to know change inherent model intelligence but to make sure structured ectraction is followed
+trainer = SFTTrainer(
+    model = model,
+    tokenizer = tokenizer,
+    train_dataset = train_dataset,
+    eval_dataset  = test_dataset,
+    args = SFTConfig(
+        dataset_text_field = "prompt",
+        max_seq_length = max_seq_length,
+        per_device_train_batch_size = 5,   
+        gradient_accumulation_steps = 5,   
+
+        warmup_steps       = 10,           
+        num_train_epochs   = 2,            
+        learning_rate      = 2e-4,         
+        lr_scheduler_type  = "linear",     
+
+        optim        = "adamw_8bit",
+        weight_decay = 0.01,               # Unsloth default (was 0.001)
+        seed         = SEED,
+
+        logging_steps  = 50,
+        report_to      = "wandb",
+
+        eval_strategy  = "steps",
+        eval_steps     = 5000,
+        save_strategy  = "steps",
+        save_steps     = 5000,
+        load_best_model_at_end  = True,    
+        metric_for_best_model   = "eval_loss",
+
+        output_dir     = "outputs_qwen35_0.8b",
+        dataset_num_proc = 8,
+        fp16= not torch.cuda.is_bf16_supported(),
+        bf16=  torch.cuda.is_bf16_supported()
+    ),
+)
+```
+![Training Overview](logs.jpg)
+
+`PS: VERY FEW EVALs WERE TAKEN FOR THE 0.8b MODEL`
+
+
+Provide the below schema for best output:
+```
+response_schema = {
+        "type": "object",
+        "properties": {
+            "key_points": {
+                "type": "array",
+                "items": {"type": "string"},
+                "nullable": True,
+            },
+            "action_items": {
+                "type": "array",
+                "items": {"type": "string"},
+                "nullable": True,
+            },
+            "summary": {"type": "string"},
+            "classification": classification_schema,
+            "callback_requested": {
+                "type": "boolean",
+                "nullable": False,
+                "description": "If the user requested a callback or mentiones currently he is busy then value is true otherwise false",
+            },
+            "callback_requested_time": {
+                "type": "string",
+                "nullable": True,
+                "description": "ISO 8601 datetime string (YYYY-MM-DDTHH:MM:SS) in the call's timezone, if user requested a callback",
+            },
+        },
+        "required": ["summary", "classification"],
+    }
+```
+
+
+
+[<img style="border-radius: 20px;" src="https://storage.googleapis.com/desivocal-prod/desi-vocal/logo.png" width="200"/>](https://ringg.ai)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+
 # Uploaded finetuned  model
 
 - **Developed by:** RinggAI
@@ -17,5 +113,3 @@ language:
 - **Finetuned from model :** Qwen/Qwen3.5-0.8B
 
 This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)