Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ 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/onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/onnx/model.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
+onnx/onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text

onnx/chat_template.jinja

@@ -0,0 +1,3 @@
+{% if messages[0]['role'] == 'system' %}<|bos|><|user_start|>{{ messages[0]['content'] }}
+
+{{ messages[1]['content'] }}<|user_end|>{% set messages = messages[2:] %}{% else %}<|bos|>{% endif %}{% for message in messages %}{% if loop.index0 % 2 == 0 %}<|user_start|>{{ message['content'] }}<|user_end|>{% else %}<|assistant_start|>{{ message['content'] }}<|assistant_end|>{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant_start|>{% endif %}

onnx/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "NanoGPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token": "<|bos|>",
+  "bos_token_id": 0,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}<|bos|><|user_start|>{{ messages[0]['content'] }}\n\n{{ messages[1]['content'] }}<|user_end|>{% set messages = messages[2:] %}{% else %}<|bos|>{% endif %}{% for message in messages %}{% if loop.index0 % 2 == 0 %}<|user_start|>{{ message['content'] }}<|user_end|>{% else %}<|assistant_start|>{{ message['content'] }}<|assistant_end|>{% endif %}{% endfor %}",
+  "dtype": "bfloat16",
+  "eos_token": "<|assistant_end|>",
+  "eos_token_id": 65531,
+  "hidden_act": "relu2",
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "logits_soft_cap": 15.0,
+  "max_position_embeddings": 2048,
+  "model_type": "nanochat",
+  "n_embd": 1280,
+  "n_head": 10,
+  "n_layer": 20,
+  "num_key_value_heads": 10,
+  "pad_token": "<|assistant_end|>",
+  "pad_token_id": 65531,
+  "qkv_bias": false,
+  "resid_dropout": 0.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "vocab_size": 65536,
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": 2,
+      "model_fp16.onnx": 1,
+      "model_q4.onnx": 1,
+      "model_q4f16.onnx": 1
+    },
+    "kv_cache_dtype": {
+      "q4f16": "float16",
+      "fp16": "float16"
+    }
+  }
+}

onnx/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d888397a4f8afcf3c120d0b0071a5a0dd641040cd4782c0316f5a40f1be2b8
+size 191419

onnx/onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c58e65e672b04216a5e28286a8a45fa08e0d2bc86c6d407b2ea1827faf11b65
+size 1909671936

onnx/onnx/model.onnx_data_1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beb6cc27be5b7e85a93a11aa93cf89afc56c4c9049d3e521bf1611a2a524e657
+size 335544320

onnx/onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df67c56aab2b644ae38b0c667bd006835b15e13bcb3175dc4d5371a738eca8b
+size 290893

onnx/onnx/model_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3c4b1c14c3f6035f373d4d24e6e1973db6486768d1222d7a0de04d332525fab
+size 1122715648

onnx/onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b81c840993bd104e39d6b333a4e42f63ce5749b6690796fb956ae431fcede8e
+size 223545

onnx/onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994c21b844cb03f673c9c40e1b7feedf301a2a0caa10915471f3b03640c56e1d
+size 634996736

onnx/onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0043592f6cc9ccbfc2485ca958ba0d5c4259cda2d6045db402d0610a9f6b14
+size 278295

onnx/onnx/model_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9ab2b7b280b54beda19fb344c127107cd57e24134acaa2f506af1977d4a702
+size 436881408

onnx/special_tokens_map.json

@@ -0,0 +1 @@
+{}

onnx/tokenizer_config.json

@@ -0,0 +1,81 @@
+{
+  "added_tokens_decoder": {
+    "65527": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65528": {
+      "content": "<|user_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65529": {
+      "content": "<|user_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65530": {
+      "content": "<|assistant_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65531": {
+      "content": "<|assistant_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65532": {
+      "content": "<|python_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65533": {
+      "content": "<|python_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65534": {
+      "content": "<|output_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65535": {
+      "content": "<|output_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}<|bos|><|user_start|>{{ messages[0]['content'] }}\n\n{{ messages[1]['content'] }}<|user_end|>{% set messages = messages[2:] %}{% else %}<|bos|>{% endif %}{% for message in messages %}{% if loop.index0 % 2 == 0 %}<|user_start|>{{ message['content'] }}<|user_end|>{% else %}<|assistant_start|>{{ message['content'] }}<|assistant_end|>{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant_start|>{% endif %}"
+}