Sarvam-1 Onnx version

.gitattributes

@@ -33,3 +33,4 @@ 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

README.md

@@ -0,0 +1,96 @@
+---
+language:
+- bn
+- en
+- gu
+- hi
+- kn
+- ml
+- mr
+- or
+- pa
+- ta
+- te
+base_model:
+- sarvamai/sarvam-1
+tags:
+- onnx
+- onnxruntime-genai
+---
+
+
+# Sarvam-1
+
+Sarvam-1 is a 2-billion parameter language model specifically optimized for Indian languages. It provides best in-class performance in 10 Indic languages (bn, gu, hi, kn, ml, mr, or, pa, ta, te) when compared with popular models like Gemma-2-2B and Llama-3.2-3B. It is also competitive against the much larger models like Llama-3.1-8B in these languages. More details can be found in our [release blog](https://www.sarvam.ai/blogs/sarvam-1).
+
+The model was trained with  [NVIDIA NeMo™ Framework](https://github.com/NVIDIA/NeMo)  on the Yotta Shakti Cloud using HGX H100 systems.
+
+*Note: This is a text-completion model. It is meant to be finetuned on downstream tasks, and cannot be used directly as a chat or an instruction-following model.*
+
+## Key Features
+
+- **Optimized for 10 Indian Languages**: Built from the ground up to support major Indian languages alongside English
+- **Superior Token Efficiency**: Achieves fertility rates of 1.4-2.1 across all supported languages, 2-4x more efficient than existing multilingual models
+- **High-Quality Training Data**: Trained on a curated corpus of ~4 trillion tokens with 2 trillion high-quality Indic tokens
+- **Efficient Inference**: 4-6x faster inference compared to larger models while matching or exceeding their performance on Indic language tasks
+
+## Model Architecture
+
+- Hidden size: 2048
+- Intermediate size: 11,008
+- Number of attention heads: 16
+- Number of hidden layers: 28
+- Number of key-value heads: 8
+- Maximum position embeddings: 8,192
+- Activation function: SwiGLU
+- Positional embeddings: Rotary (RoPE) with theta=10,000
+- Training: Grouped-query attention and bfloat16 mixed-precision
+
+## Performance
+
+### Translated Academic Benchmarks (Zero-shot)
+
+- MMLU: 44.44
+- ARC-Challenge: 58.50
+- TriviaQA: 90.62
+- BoolQ: 80.68
+
+### IndicGenBench (One-shot)
+
+- Flores English-to-Indic translation: 39.83 chrF++
+- CrossSum: 20.48 chrF++
+- XORQA: 25.27 F1
+- XQUAD: 41.58 F1
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load model and tokenizer
+model = AutoModelForCausalLM.from_pretrained("sarvamai/sarvam-1")
+tokenizer = AutoTokenizer.from_pretrained("sarvamai/sarvam-1")
+
+# Example usage
+text = "कर्नाटक की राजधानी है:"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=5)
+result = tokenizer.decode(outputs[0])
+```
+
+## Training Details
+
+- Training Infrastructure: Yotta's Shakti cluster
+- Hardware: 1,024 GPUs
+- Training Duration: 5 days
+- Framework: NVIDIA NeMo
+
+## License
+
+Sarvam non-commercial license: See the [LICENSE](LICENSE.md) file
+
+## Acknowledgements
+
+- NVIDIA: for support with the NeMo codebase
+- Yotta: for sccess to the Shakti GPU cluster
+- AI4Bharat: for their academic partnership and expertise in Indian language technologies

chat_template.jinja

@@ -0,0 +1,22 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}
+{% for message in loop_messages %}
+{% if message['role'] not in ['user', 'assistant', 'tool_calls'] %}
+{{ raise_exception('Invalid role: ' + message['role'] + '. Must be user, assistant, or tool_calls.') }}
+{% endif %}
+{% if loop.index0 == 0 and system_message != false %}
+{% set content = '<<SYS>>
+' + system_message + '
+<</SYS>>
+
+' + message['content'] %}
+{% else %}
+{% set content = message['content'] %}
+{% endif %}
+{% if message['role'] == 'user' %}
+{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}
+{% elif message['role'] == 'assistant' %}
+{{ ' ' + content.strip() + ' ' + eos_token }}
+{% elif message['role'] == 'tool_calls' %}
+{{ ' [TOOL_CALLS] ' + content.strip() + ' [/TOOL_CALLS] ' }}
+{% endif %}
+{% endfor %}

genai_config.json

@@ -0,0 +1,50 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 8192,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 2048,
+            "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": 16,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 8
+        },
+        "eos_token_id": 2,
+        "pad_token_id": 2,
+        "type": "llama",
+        "vocab_size": 68096
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": true,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 8192,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": false,
+        "repetition_penalty": 1.05,
+        "temperature": 0.1,
+        "top_k": 1,
+        "top_p": 0.95
+    }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a67a9abca05d823c965fe6220c2377c3da26d588929d427e52937eebac972f3
+size 655872

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ac2b750fc9664f5310cf45e91f634bc4216ffb7bfccf2708c7de61c69b77e4
+size 5052301312

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd33409a577e8b416247587b0f5bd7a3eec245a1f18d4ec7793ff299ad3fbe2
+size 1935856