Add model file

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.onnx.data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,72 @@
----
-license: gpl-3.0
----
+---
+base_model:
+- sarvamai/sarvam-translate
+license: gpl-3.0
+tags:
+- gemma3
+- indic
+- onnx
+- onnxruntime-genai
+- sarvam
+- text-generation-inference
+- transformers
+- translation
+language:
+- as
+- bn
+- brx
+- doi
+- gom
+- gu
+- en
+- hi
+- kn
+- ks
+- mai
+- ml
+- mni
+- mr
+- ne
+- or
+- pa
+- sa
+- sat
+- sd
+- ta
+- te
+- ur
+base_model_relation: quantized
+---
+
+# Uploaded  model
+
+- **Converted by:** Prince-1
+- **License:** gpl-3.0
+- **Original model :** sarvamai/sarvam-translate
+
+# Sarvam-Translate
+<p align="center">
+  <a href="https://dashboard.sarvam.ai/translate"
+     target="_blank" rel="noopener noreferrer">
+    <img
+      src="https://img.shields.io/badge/🚀 Try on Sarvam&nbsp;Playground-1488CC?style=for-the-badge&logo=rocket"
+      alt="Try on Sarvam Playground"
+    />
+  </a>
+</p>
+Sarvam-Translate is an advanced translation model from Sarvam AI, specifically designed for comprehensive, document-level translation across the 22 official Indian languages, built on Gemma3-4B-IT. It addresses modern translation needs by moving beyond isolated sentences to handle long-context inputs, diverse content types, and various formats. Sarvam-Translate aims to provide high-quality, contextually aware translations for Indian languages, which have traditionally lagged behind high-resource languages in LLM performance.
+
+Learn more about Sarvam-Translate in our detailed [blog post](https://www.sarvam.ai/blogs/sarvam-translate).
+
+## Key Features
+- **Comprehensive Indian Language Support**: Focus on the 22 official Indian languages, ensuring nuanced and accurate translations.
+- **Advanced Document-Level Translation**: Translates entire documents, web pages, speeches, textbooks, and scientific articles, not just isolated sentences.
+- **Versatile Format Handling**: Processes a wide array of input formats, including markdown, digitized content (handling OCR errors), documents with embedded math and chemistry equations, and code files (translating only comments).
+- **Context-Aware & Inclusive**: Engineered to respect different contexts, formats, styles (formal/informal), and ensure inclusivity (e.g., appropriate gender attribution).
+
+## Supported languages list
+
+`Assamese`, `Bengali`, `Bodo`, `Dogri`, `Gujarati`, `English`, `Hindi`, `Kannada`, `Kashmiri`, `Konkani`, `Maithili`, `Malayalam`, `Manipuri`, `Marathi`, `Nepali`, `Odia`, `Punjabi`, `Sanskrit`, `Santali`, `Sindhi`, `Tamil`, `Telugu`, `Urdu`
+
+## Covertion 
+The onnx model is created using [onnxruntime-genai](https://github.com/microsoft/onnxruntime-genai)

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

genai_config.json

@@ -0,0 +1,59 @@
+{
+    "model": {
+        "bos_token_id": 2,
+        "context_length": 131072,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": [
+                    {
+                        "cuda": {
+                            "enable_cuda_graph": "0"
+                        }
+                    }
+                ]
+            },
+            "filename": "model.onnx",
+            "head_size": 256,
+            "hidden_size": 2560,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "position_ids": "position_ids",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 8,
+            "num_hidden_layers": 34,
+            "num_key_value_heads": 4
+        },
+        "eos_token_id": [
+            1,
+            106
+        ],
+        "pad_token_id": 0,
+        "type": "gemma3",
+        "vocab_size": 262208
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": true,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 131072,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 0.95
+    }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a228b5388b2398774e54af0354d6b52574059bdd0521aeb0a09620ebf67916a
+size 456903

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e426b9b91d37457d597899b70f87978ad1563373f31def06fc6a296ec20f3957
+size 9237985280

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074