Converted maya-research/Veena model to onnx format

.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

genai_config.json

@@ -0,0 +1,50 @@
+{
+    "model": {
+        "bos_token_id": 128000,
+        "context_length": 131072,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 3072,
+            "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": 24,
+            "num_hidden_layers": 28,
+            "num_key_value_heads": 8
+        },
+        "eos_token_id": 128001,
+        "pad_token_id": 128001,
+        "type": "llama",
+        "vocab_size": 156951
+    },
+    "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": false,
+        "repetition_penalty": 1.0,
+        "temperature": 0.6,
+        "top_k": 1,
+        "top_p": 0.9
+    }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788a3bedfdd58e570ed1e27deaaa17e2b4fb1ab304fd68d0055d199eb066c9fd
+size 653878

model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c688c9b0cad401d142e569092e1becb86bd27430cf8fc1687662688ea0e0705
+size 7599663104

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<spk_kavya>",
+    "<spk_apsara>",
+    "<spk_agastya>",
+    "<spk_vinaya>",
+    "<spk_maitri>",
+    "<spk_charu>",
+    "<spk_ishana>",
+    "<spk_kyra>",
+    "<spk_mohini>",
+    "<spk_varun>",
+    "<spk_soumya>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<custom_token_7>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88f202c5216ed6485367f5a606093d54f9a89ef3c654001ccc10026fcd276f2
+size 22851621