Upload optimized ONNX model

chat_template.jinja

@@ -1,93 +1,9 @@
-{{- bos_token }}
-{%- if custom_tools is defined %}
-    {%- set tools = custom_tools %}
-{%- endif %}
-{%- if not tools_in_user_message is defined %}
-    {%- set tools_in_user_message = true %}
-{%- endif %}
-{%- if not date_string is defined %}
-    {%- if strftime_now is defined %}
-        {%- set date_string = strftime_now("%d %b %Y") %}
-    {%- else %}
-        {%- set date_string = "26 Jul 2024" %}
-    {%- endif %}
-{%- endif %}
-{%- if not tools is defined %}
-    {%- set tools = none %}
-{%- endif %}
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif USE_DEFAULT_PROMPT == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'DEFAULT_SYSTEM_MESSAGE' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>
+' + system_message + '
+<</SYS>>
 
-{#- This block extracts the system message, so we can slot it into the right place. #}
-{%- if messages[0]['role'] == 'system' %}
-    {%- set system_message = messages[0]['content']|trim %}
-    {%- set messages = messages[1:] %}
-{%- else %}
-    {%- set system_message = "" %}
-{%- endif %}
+' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>
+' + content.strip() + '
+<</SYS>>
 
-{#- System message #}
-{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
-{%- if tools is not none %}
-    {{- "Environment: ipython\n" }}
-{%- endif %}
-{{- "Cutting Knowledge Date: December 2023\n" }}
-{{- "Today Date: " + date_string + "\n\n" }}
-{%- if tools is not none and not tools_in_user_message %}
-    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
-    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
-    {{- "Do not use variables.\n\n" }}
-    {%- for t in tools %}
-        {{- t | tojson(indent=4) }}
-        {{- "\n\n" }}
-    {%- endfor %}
-{%- endif %}
-{{- system_message }}
-{{- "<|eot_id|>" }}
-
-{#- Custom tools are passed in a user message with some extra guidance #}
-{%- if tools_in_user_message and not tools is none %}
-    {#- Extract the first user message so we can plug it in here #}
-    {%- if messages | length != 0 %}
-        {%- set first_user_message = messages[0]['content']|trim %}
-        {%- set messages = messages[1:] %}
-    {%- else %}
-        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
-{%- endif %}
-    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
-    {{- "Given the following functions, please respond with a JSON for a function call " }}
-    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
-    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
-    {{- "Do not use variables.\n\n" }}
-    {%- for t in tools %}
-        {{- t | tojson(indent=4) }}
-        {{- "\n\n" }}
-    {%- endfor %}
-    {{- first_user_message + "<|eot_id|>"}}
-{%- endif %}
-
-{%- for message in messages %}
-    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
-        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
-    {%- elif 'tool_calls' in message %}
-        {%- if not message.tool_calls|length == 1 %}
-            {{- raise_exception("This model only supports single tool-calls at once!") }}
-        {%- endif %}
-        {%- set tool_call = message.tool_calls[0].function %}
-        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
-        {{- '{"name": "' + tool_call.name + '", ' }}
-        {{- '"parameters": ' }}
-        {{- tool_call.arguments | tojson }}
-        {{- "}" }}
-        {{- "<|eot_id|>" }}
-    {%- elif message.role == "tool" or message.role == "ipython" %}
-        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
-        {%- if message.content is mapping or message.content is iterable %}
-            {{- message.content | tojson }}
-        {%- else %}
-            {{- message.content }}
-        {%- endif %}
-        {{- "<|eot_id|>" }}
-    {%- endif %}
-{%- endfor %}
-{%- if add_generation_prompt %}
-    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
-{%- endif %}
+' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}

config.json

@@ -4,36 +4,31 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
+  "bos_token_id": 0,
   "dtype": "float32",
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
-  "head_dim": 8,
+  "eos_token_id": 1,
+  "head_dim": 4,
   "hidden_act": "silu",
-  "hidden_size": 32,
+  "hidden_size": 16,
   "initializer_range": 0.02,
   "intermediate_size": 64,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "num_key_value_heads": 2,
-  "pad_token_id": null,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_parameters": {
-    "factor": 32.0,
-    "high_freq_factor": 4.0,
-    "low_freq_factor": 1.0,
-    "original_max_position_embeddings": 8192,
-    "rope_theta": 500000.0,
-    "rope_type": "llama3"
+    "rope_theta": 10000.0,
+    "rope_type": "default"
   },
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000,
   "transformers.js_config": {
     "use_external_data_format": {
       "model.onnx": 1,
@@ -43,8 +38,5 @@
       "q4f16": "float16",
       "fp16": "float16"
     }
-  },
-  "transformers_version": "5.3.0.dev0",
-  "use_cache": true,
-  "vocab_size": 128256
+  }
 }

generation_config.json

@@ -1,10 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
   "transformers_version": "5.3.0.dev0"
 }

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ccf434548b8919f42b3f0eba20e3145c1e9f3592821ef24810bcfba4156a5c
-size 21471
+oid sha256:df31996713fd6e584f1e1961bb9f70674306447cd7362e8792e2ae51af529f38
+size 21102

onnx/model.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f65f40647b300be84f62c0872c0498f3b9d01f4b965cfac95a315c1f0c696a1
-size 20684800
+oid sha256:bc620771b792cf5c0667048c4157a34a90872c7c3e1da3a15bcce4a490b35857
+size 4161536

onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7aaaf4a1dccab0eb8ff69d1b0c0488534df6c2d8c0d815ca7e34c85f52ce1b
-size 21183
+oid sha256:2d7a87e856f8ffa899a806f5a65aa028d0183f4ebc295bf155b90c547872cffd
+size 24553

onnx/model_fp16.onnx_data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34ac854ebe75f1e3542322b180e6f62497865626a041e8f529d3cde12403f65
-size 10342400
+oid sha256:c70d822354c8df524bc3c2a9d98cae8e93667794006691709fede5118707a60b
+size 2076672

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a223ade375cc1d13b04e897ce1d36a04f50140e1ba3d107021ea68d4b5e614c
-size 11574638
+oid sha256:9c5992569a6744ca7b5fa6807ec215340d7e0d7b5c4c6bc3d100f0e3469c7d83
+size 1879442

tokenizer_config.json

@@ -1,14 +1,14 @@
 {
+  "add_prefix_space": null,
   "backend": "tokenizers",
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
   "is_local": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "tokenizer_class": "TokenizersBackend",
-  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif USE_DEFAULT_PROMPT == true and not '<<SYS>>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'DEFAULT_SYSTEM_MESSAGE' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\n' + content.strip() + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}"
 }