Upload folder using huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "RajuKandasamy/tamillama_tiny_30m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 786,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": false
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb78dc2f1c5299eaad59f93311a58bae9a05729b5868e618cce89202bdf1623
+size 122063009

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd8b4ce2984ab0513d0b45387af4495b7ab1847fdc3c0c1a49a6b28d0f3e08c
+size 123158321

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caa37c4cebcabe4be245d757c4ba49b7f947affa91887be3141c980dda14bb2
+size 33048128

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5cdda076d1b9032209af769406e28ddd45c8b4a5e63b556229a49fbfd9f5baf
+size 31653003

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ea01e7681a85a7683d45ac32dfa120f4a727db54f414fe8335f1963d6574a6
+size 122074560

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cf15031ad3ea5d12e50facb4e396a18c5a1b910f19a263822f9df36d4d7a6c
+size 31667200

quantize_config.json

@@ -0,0 +1,107 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Identity",
+                "Range",
+                "Expand",
+                "If",
+                "Add",
+                "Concat",
+                "Transpose",
+                "Pow",
+                "Sigmoid",
+                "ReduceMean",
+                "Equal",
+                "Shape",
+                "Reshape",
+                "Where",
+                "Cast",
+                "Constant",
+                "Less",
+                "ConstantOfShape",
+                "Slice",
+                "Mul",
+                "Squeeze",
+                "MatMul",
+                "Div",
+                "Unsqueeze",
+                "Gather",
+                "Softmax",
+                "Neg",
+                "Sqrt",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Identity",
+                "Range",
+                "If",
+                "Expand",
+                "Add",
+                "Concat",
+                "Transpose",
+                "Pow",
+                "Sigmoid",
+                "ReduceMean",
+                "Equal",
+                "Shape",
+                "Reshape",
+                "Where",
+                "Cast",
+                "Constant",
+                "Less",
+                "ConstantOfShape",
+                "Slice",
+                "Mul",
+                "Squeeze",
+                "MatMul",
+                "Div",
+                "Unsqueeze",
+                "Gather",
+                "Softmax",
+                "Neg",
+                "Sqrt",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Identity",
+                "Range",
+                "Expand",
+                "If",
+                "Add",
+                "Concat",
+                "Transpose",
+                "Pow",
+                "Sigmoid",
+                "ReduceMean",
+                "Equal",
+                "Shape",
+                "Reshape",
+                "Where",
+                "Cast",
+                "Constant",
+                "ConstantOfShape",
+                "Mul",
+                "Slice",
+                "Squeeze",
+                "MatMul",
+                "Div",
+                "Unsqueeze",
+                "Gather",
+                "Softmax",
+                "Neg",
+                "Sqrt",
+                "Sub"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dd6b7bc2edb9eb352bcc155235952e2c0601b6a245025176939eb7ecfeb861
+size 1179251

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}