Upload folder using huggingface_hub

.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
+onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0204ebfd240f051077b1c87101782d6ca87744f0aca848f78abe0369eca02d9
+size 2109343

onnx/decoder_model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b463b7ffd6e136c6d38b736b108c47ccc30314c76339fa300cc8a20860001b4
+size 13200580608

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f62d9718c27a5808dae6b9b368cf80f64274a4709778c555ecc44a5b14928dc
+size 1102921872

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c06286b9fac4dc5b434c08c9da2ca967f170fb67f77db881aef29103945d08
+size 2136863

onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b08b7ce45cdef33d82b2b05ad1b01b0785594fd1999a37a3389120f396efe87
+size 4400193536

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9880af86324b560bef95572f1c058b42930a96bef4d26175260485218af163
+size 1102958700

quantize_config.json

@@ -0,0 +1,70 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "ReduceMean",
+                "Sigmoid",
+                "Reshape",
+                "Neg",
+                "Equal",
+                "MatMul",
+                "Squeeze",
+                "Expand",
+                "Pow",
+                "Concat",
+                "ConstantOfShape",
+                "Unsqueeze",
+                "Slice",
+                "Gather",
+                "Softmax",
+                "Sqrt",
+                "Transpose",
+                "Range",
+                "Div",
+                "Constant",
+                "Where",
+                "Cast",
+                "Less",
+                "Shape",
+                "Add",
+                "Sub",
+                "Mul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "ReduceMean",
+                "Sigmoid",
+                "Reshape",
+                "Neg",
+                "Equal",
+                "MatMul",
+                "Squeeze",
+                "Expand",
+                "Pow",
+                "Concat",
+                "ConstantOfShape",
+                "Unsqueeze",
+                "Slice",
+                "Gather",
+                "Softmax",
+                "Sqrt",
+                "Transpose",
+                "Range",
+                "Div",
+                "Constant",
+                "Where",
+                "Cast",
+                "Less",
+                "Shape",
+                "Add",
+                "Sub",
+                "Mul"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}