Upload folder using huggingface_hub

.gitattributes

@@ -34,5 +34,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_int8.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
+onnx/model_uint8.onnx_data filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,42 +1,38 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "nguyenthanhthuan/Llama_3.2_1B_Intruct_Tool_Calling_V2",
+  "_name_or_path": "NousResearch/DeepHermes-3-Llama-3-8B-Preview",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 64,
+  "eos_token_id": 128009,
+  "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 2048,
+  "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
+  "intermediate_size": 14336,
   "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 16,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
-    "factor": 32.0,
+    "factor": 8.0,
     "high_freq_factor": 4.0,
     "low_freq_factor": 1.0,
     "original_max_position_embeddings": 8192,
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "transformers_version": "4.46.3",
-  "unsloth_version": "2024.10.7",
+  "unsloth_fixed": true,
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
   "do_sample": true,
   "eos_token_id": [

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5f9e5b9f911961b179a4688efbb50b616ecd66342b0faf9da0b78a0e691e6d
-size 435319
+oid sha256:bdd315c3543dc1c2c7fea02fee19dcc5988b3bf455365892132e0f1ed01f5b3f
+size 858913

onnx/model.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f269b9750ade29e17b6daec21c5d76bf2f0c1206b9e8e1090a2ad2d3b1ef95
-size 4943257600
+oid sha256:2fe497e51b001cf53241abf12fd69a9561cb75e6290a7ef41b94d5519499e832
+size 32121044992

onnx/model_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b933289dbe1f9af7c3547f17c68fc157e5862960006d9e7c27522b6cdb4cea
-size 1598743831
+oid sha256:c078b3be1198c2ef021344f5ce42438cf55beaa2315d635b20c457a4b90c6684
+size 911812

onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:957b23c342e124cd7ffff7de2275b5b30a27f54d8cfee8f6a426ae1663d64e68
-size 436000
+oid sha256:76fcb21a89369fc32d3795df146930abb06c163443824f4f1ec2d90bb69b03d7
+size 860108

onnx/model_fp16.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9733aab730ec38ed1ed2b8e85ba96773627c212e41c4faec2771f3163968ad1
-size 2471628800
+oid sha256:02911f28a0354c44876f3329ecf587d5ca16e65698bb2869937d8544d652aeaa
+size 16060522496

onnx/model_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827ec32473381c80c4a147332bf3bf7b9b6682ba15dd6da0f20f12457ca28071
-size 1236565479
+oid sha256:5b1bb76d6a54817b3f2520fcd98dc4e95dcbc9bfc0ce7c57dca96c16e4c2b2dd
+size 1105763

onnx/model_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54166d51772c5e300692fd1893ca72be7d91b92fa951c15d11c042992757680
-size 1659560375
+oid sha256:3827b6b586a90af38f1f11a34192dbc80f08b3e8e30deeb68253b7dd1c4153fb
+size 908949

onnx/model_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d37c47b5284b00dac46b21d04ea204f336424925e7f1e5fd3536140f815390
-size 1073271141
+oid sha256:6c7183ef2e2436a57314ca1603bbd407219c03ac137b8eef75ff92c4163f9631
+size 910416

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827ec32473381c80c4a147332bf3bf7b9b6682ba15dd6da0f20f12457ca28071
-size 1236565479
+oid sha256:92209e407f1d3bf3bebc152743293fb7a3a4ec00fe2e514bbb378cc94796dac9
+size 1107250

onnx/model_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17af458ac90f9069de8f87cf5c38620c954f24fa73ef7eff32bd159427947a9d
-size 1236565541
+oid sha256:0c9ed7e84bdb801d0e4a6606067eac6ae14dd76948b408ca9f49bc7475599665
+size 1106175

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|finetune_right_pad_id|>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2050,15 +2051,26 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "\n{%- if messages[0]['role'] == 'system' -%}\n<|start_header_id|>system<|end_header_id|>\n\n{{ messages[0]['content'] }}\n{%- endif -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'user' -%}\n        <|start_header_id|>user<|end_header_id|>\n        {{ message['content'] }}\n    {%- elif message['role'] in ['assistant'] -%}\n        <|start_header_id|>assistant<|end_header_id|>\n        {{ message['content'] }}<|eot_id|>\n    {%- elif message['role'] in ['tool_call'] -%}\n        <|start_header_id|>tool_call<|end_header_id|>\n        {{ message['content'] }}<|eot_id|>\n    {%- elif message['role'] == 'tool_response' -%}\n        <|start_header_id|>tool_respone<|end_header_id|>\n        {{ message['content'] }}\n    {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%} <|start_header_id|>assistant<|end_header_id|>\n{%- endif -%}\n",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|finetune_right_pad_id|>",
+  "pad_token": "<|end_of_text|>",
   "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
 }