Add Stage 1 LoRA-merged Q4 ONNX export

.gitattributes

@@ -33,3 +33,4 @@ 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/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,115 @@
+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + arg_value + "'" -}}
+    {%- elif arg_value is mapping -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- else -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set _ns.result = _ns.result + item["text"] -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func_name = tool_call["function"]["name"] -%}
+        {%- set func_args = tool_call["function"]["arguments"] -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- for arg_name, arg_value in func_args.items() -%}
+            {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+        {%- endfor -%}
+        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+    {%- endfor -%}
+    {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+            {{- "<think>" + message.thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- if message.content is defined -%}
+            {%- set content = parse_content(message.content) -%}
+            {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
+                {%- if "</think>" in content -%}
+                    {%- set content = content.split("</think>")[-1] | trim -%}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
+                {%- set _has_cfm = true -%}
+                {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+                {{- content[:_trunc_len] -}}
+            {%- else -%}
+                {{- content -}}
+            {%- endif -%}
+        {%- endif -%}
+        {%- if message.tool_calls is defined -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block__name_mlp": "parallel_mlp_merged",
+  "block_auto_adjust_ff_dim": false,
+  "block_dim": 1024,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_ffn_te_autocast": false,
+  "block_ffn_use_quantized_params": false,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_sequence_parallel_norm_across_tp": false,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1024,
+  "conv_use_xavier_init": true,
+  "dtype": "float16",
+  "eos_token_id": 7,
+  "ffn_te_autocast": false,
+  "ffn_use_quantized_params": false,
+  "full_attn_idxs": null,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_heads": 16,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sequence_parallel_norm_across_tp": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.1",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp32": "float32"
+    },
+    "use_external_data_format": true
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "4.54.0"
+}

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a442c44d3d143432edff57984a4e7e8da65179d3a960a170d294aed8c5dd8d
+size 154010

onnx/model_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cd5849e4ad4ed619293d6038012999ce49dc6ef07c0ec1c608d0d72c8e0251
+size 211111936

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true,
+  "chat_template": "{{- bos_token -}}\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n\n{%- macro format_arg_value(arg_value) -%}\n    {%- if arg_value is string -%}\n        {{- \"'\" + arg_value + \"'\" -}}\n    {%- elif arg_value is mapping -%}\n        {{- arg_value | tojson -}}\n    {%- else -%}\n        {{- arg_value | string -}}\n    {%- endif -%}\n{%- endmacro -%}\n\n{%- macro parse_content(content) -%}\n    {%- if content is string -%}\n        {{- content -}}\n    {%- else -%}\n        {%- set _ns = namespace(result=\"\") -%}\n        {%- for item in content -%}\n            {%- if item[\"type\"] == \"image\" -%}\n                {%- set _ns.result = _ns.result + \"<image>\" -%}\n            {%- elif item[\"type\"] == \"text\" -%}\n                {%- set _ns.result = _ns.result + item[\"text\"] -%}\n            {%- else -%}\n                {%- set _ns.result = _ns.result + item | tojson -%}\n            {%- endif -%}\n        {%- endfor -%}\n        {{- _ns.result -}}\n    {%- endif -%}\n{%- endmacro -%}\n\n{%- macro render_tool_calls(tool_calls) -%}\n    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}\n    {%- for tool_call in tool_calls -%}\n        {%- set func_name = tool_call[\"function\"][\"name\"] -%}\n        {%- set func_args = tool_call[\"function\"][\"arguments\"] -%}\n        {%- set args_ns = namespace(arg_strings=[]) -%}\n        {%- for arg_name, arg_value in func_args.items() -%}\n            {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + \"=\" + format_arg_value(arg_value)] -%}\n        {%- endfor -%}\n        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + \"(\" + (args_ns.arg_strings | join(\", \")) + \")\"] -%}\n    {%- endfor -%}\n    {{- \"<|tool_call_start|>[\" + (tool_calls_ns.tool_calls | join(\", \")) + \"]<|tool_call_end|>\" -}}\n{%- endmacro -%}\n\n{%- set ns = namespace(system_prompt=\"\", last_user_index=-1) -%}\n{%- if messages[0][\"role\"] == \"system\" -%}\n    {%- if messages[0].get(\"content\") -%}\n        {%- set ns.system_prompt = parse_content(messages[0][\"content\"]) -%}\n    {%- endif -%}\n    {%- set messages = messages[1:] -%}\n{%- endif -%}\n{%- if tools -%}\n    {%- set ns.system_prompt = ns.system_prompt + (\"\\n\" if ns.system_prompt else \"\") + \"List of tools: [\" -%}\n    {%- for tool in tools -%}\n        {%- if tool is not string -%}\n            {%- set tool = tool | tojson -%}\n        {%- endif -%}\n        {%- set ns.system_prompt = ns.system_prompt + tool -%}\n        {%- if not loop.last -%}\n            {%- set ns.system_prompt = ns.system_prompt + \", \" -%}\n        {%- endif -%}\n    {%- endfor -%}\n    {%- set ns.system_prompt = ns.system_prompt + \"]\" -%}\n{%- endif -%}\n{%- if ns.system_prompt -%}\n    {{- \"<|im_start|>system\\n\" + ns.system_prompt + \"<|im_end|>\\n\" -}}\n{%- endif -%}\n{%- for message in messages -%}\n    {%- if message[\"role\"] == \"user\" -%}\n        {%- set ns.last_user_index = loop.index0 -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n    {{- \"<|im_start|>\" + message.role + \"\\n\" -}}\n    {%- if message.role == \"assistant\" -%}\n        {%- generation -%}\n        {%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}\n            {{- \"<think>\" + message.thinking + \"</think>\" -}}\n        {%- endif -%}\n        {%- set _cfm_tag = \"CONTINUE_FINAL_MESSAGE_TAG \" -%}\n        {%- set _has_cfm = false -%}\n        {%- if message.content is defined -%}\n            {%- set content = parse_content(message.content) -%}\n            {%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}\n                {%- if \"</think>\" in content -%}\n                    {%- set content = content.split(\"</think>\")[-1] | trim -%}\n                {%- endif -%}\n            {%- endif -%}\n            {%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}\n                {%- set _has_cfm = true -%}\n                {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}\n                {{- content[:_trunc_len] -}}\n            {%- else -%}\n                {{- content -}}\n            {%- endif -%}\n        {%- endif -%}\n        {%- if message.tool_calls is defined -%}\n            {{- render_tool_calls(message.tool_calls) -}}\n        {%- endif -%}\n        {%- if _has_cfm -%}\n            {{- _cfm_tag -}}\n        {%- endif -%}\n        {{- \"<|im_end|>\\n\" -}}\n        {%- endgeneration -%}\n    {%- else %}\n        {%- if message.get(\"content\") -%}\n            {{- parse_content(message[\"content\"]) -}}\n        {%- endif -%}\n        {{- \"<|im_end|>\\n\" -}}\n    {%- endif %}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{- \"<|im_start|>assistant\\n\" -}}\n{%- endif -%}"
+}