Publish OpenCal base LFM2.5-VL-450M ONNX (transformers.js)

.gitattributes

@@ -1,35 +1,5 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
+*.onnx_data filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+  - lfm2
+  - vision
+  - multimodal
+  - food
+  - calories
+  - nutrition
+  - onnx
+  - transformers.js
+license: apache-2.0
+base_model: LiquidAI/LFM2.5-VL-450M
+model-type: lfm2_vl
+---
+
+# OpenCal Base
+
+**OpenCal Base** is a LFM2.5-VL-450M fine-tune that reads food photos (and text) and
+outputs structured ingredient + gram-weight extractions aligned to the USDA food
+database. It is exported to ONNX for the `@huggingface/transformers.js` browser
+runtime (WebGPU / WASM / CPU).
+
+## Model details
+
+| Field | Value |
+| --- | --- |
+| Base model | [`LiquidAI/LFM2.5-VL-450M`](https://huggingface.co/LiquidAI/LFM2.5-VL-450M) |
+| Fine-tune | LoRA, OpenCal v6 (gram-weight + kcal/macro target) |
+| Architecture | `Lfm2VlForConditionalGeneration` (`model_type: lfm2_vl`) |
+| Runtime | ONNX / transformers.js (WebGPU, WASM, CPU) |
+| License | Apache-2.0 |
+
+## Fine-tune summary
+
+LoRA on top of the frozen base, merged weights. Target format is a JSON list of
+`{name, grams, kcal, protein_g, carbs_g, fat_g}` extracted per item, with grams
+normalized per 100 g and macros sourced from USDA data. The model is used by the
+OpenCal app to turn a photo or a text description of a meal into per-item
+nutrition.
+
+### Benchmark results (OpenCal internal evals)
+
+- **F101** (full meals, median gold kcal ≈ 293): kcal MAE **243**, WAPE **41.5%**,
+  within-50% of gold **70.4%**.
+- **N5k** (lab samples, median gold kcal ≈ 43): ingredient-identity recall
+  baseline **76.4%**, this model **84.4%** (reference LLM **73.6%**).
+
+## Usage (transformers.js)
+
+```js
+import { AutoModelForImageTextToText, AutoProcessor, RawImage } from '@huggingface/transformers';
+
+const processor = await AutoProcessor.from_pretrained('OpenCal/opencal-base');
+const model = await AutoModelForImageTextToText.from_pretrained('OpenCal/opencal-base', { dtype: 'auto', device: 'webgpu' });
+
+const image = await RawImage.fromURL('https://example.com/meal.jpg');
+const texts = ['List the ingredients and their amounts in grams'];
+
+const { inputs } = await processor(image, texts, { return_tensor: false });
+const { logits } = await model(inputs);
+const decoded = processor.batch_decode(logits[1].id); // [1] for single sample
+console.log(decoded[0]);
+```
+
+## File layout (ONNX)
+
+The model is split into the standard LFM2.5-VL ONNX components. The suffix of each
+weight file selects the runtime/precision:
+
+| File | Precision | Use |
+| --- | --- | --- |
+| `embed_tokens{,_fp16,_q4,_quantized}.onnx` | fp32 / fp16 / q4 / q8 | input embeddings (`input_ids → inputs_embeds`) |
+| `decoder_model_merged{,_fp16,_q4,_q4f16}.onnx` | fp32 / fp16 / q4 / q4f16 | text decoder (main body) |
+| `vision_encoder{,_fp16,_q4,_quantized}.onnx` | fp32 / fp16 / q4 / q8 | vision encoder |
+
+- `q4f16` — MatMulNBits q4 weights with fp16 scales / KV cache (WebGPU production path).
+- `quantized` (= q8, `MatMulNBits`) — WASM path.
+- `fp16` — 16-bit WebGPU path.
+
+`tokenizer.json`, `preprocessor_config.json`, `config.json`, and
+`generation_config.json` are at the repository root.
+
+## Citation / base model
+
+This model derives from `LiquidAI/LFM2.5-VL-450M`. Please see the base repository
+for the original weights and paper.

chat_template.jinja

@@ -0,0 +1,92 @@
+{{- bos_token -}}
+{%- set keep_past_thinking = keep_past_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_assistant_index=-1) -%}
+{%- if messages[0].role == "system" -%}
+    {%- if messages[0].content is defined -%}
+        {%- 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\n" if ns.system_prompt else "") + "Today's date: " + strftime_now("%Y-%m-%d") + "\n\nList of tools: " + (tools | tojson) -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message.role == "assistant" -%}
+        {%- set ns.last_assistant_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 (keep_past_thinking or loop.index0 == ns.last_assistant_index) -%}
+            {{- "<think>" + message.thinking + "</think>" -}}
+        {%- endif -%}
+        {%- if message.tool_calls is defined -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if message.content is defined -%}
+            {%- set content = parse_content(message.content) -%}
+            {%- if not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
+                {%- if "</think>" in content -%}
+                    {%- set content = content.split("</think>")[-1] | trim -%}
+                {%- endif -%}
+            {%- endif -%}
+            {{- content + ("" if (continue_final_message and loop.last) else "<|im_end|>\n") -}}
+        {%- endif -%}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.content is defined -%}
+            {{- parse_content(message.content) + "<|im_end|>\n" -}}
+        {%- endif -%}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,103 @@
+{
+  "architectures": [
+    "Lfm2VlForConditionalGeneration"
+  ],
+  "do_image_splitting": true,
+  "downsample_factor": 2,
+  "dtype": "bfloat16",
+  "encoder_patch_size": 16,
+  "image_token_id": 396,
+  "max_image_tokens": 256,
+  "max_pixels_tolerance": 2.0,
+  "max_tiles": 10,
+  "min_image_tokens": 64,
+  "min_tiles": 2,
+  "model_type": "lfm2_vl",
+  "projector_bias": true,
+  "projector_hidden_act": "gelu",
+  "projector_hidden_size": 2048,
+  "projector_use_layernorm": false,
+  "text_config": {
+    "_name_or_path": "LiquidAI/LFM2-350M",
+    "architectures": [
+      "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": true,
+    "block_dim": 1024,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_mlp_init_scale": 1.0,
+    "block_multiple_of": 256,
+    "block_norm_eps": 1e-05,
+    "block_out_init_scale": 1.0,
+    "block_use_swiglu": true,
+    "block_use_xavier_init": true,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 1024,
+    "conv_dim_out": 1024,
+    "conv_use_xavier_init": true,
+    "dtype": "bfloat16",
+    "eos_token_id": 7,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 6656,
+    "layer_types": [
+      "conv",
+      "conv",
+      "full_attention",
+      "conv",
+      "conv",
+      "full_attention",
+      "conv",
+      "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": 16,
+    "num_key_value_heads": 8,
+    "rope_parameters": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+  },
+  "tile_size": 512,
+  "transformers_version": "5.0.0.dev0",
+  "use_image_special_tokens": true,
+  "use_thumbnail": true,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip2_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_patches": 256,
+    "patch_size": 16,
+    "vision_use_head": false
+  },
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "vision_encoder": true,
+      "embed_tokens": true,
+      "decoder_model_merged": 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": "4.57.0"
+}

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0e0195c934b3a038e88fb737ee49d1e3c677348d30bc410f9b61a8b91e9cd8
+size 143084

onnx/decoder_model_merged.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:429ed2a9ee7dee62d986ea56c0bb926faff679564526c80e297c87a757fa1780
+size 1450700800

onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4128700047fb544477d3d385384cd9e9ef429706d4f23522c0c1b99525f0ef00
+size 148963

onnx/decoder_model_merged_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3976377d486ddb1af3a20eab8c745c02c590aac60a9c0e74f99bac6b0da5573
+size 725350400

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26600302bd9db0ef26d1a98fba0aae22dac99468e2195ce6d9b9bc7308c18f68
+size 171898

onnx/decoder_model_merged_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dda301667af570f62f558049d16a7dcbd12ab182cab25f533213b8fe9281594
+size 481030144

onnx/decoder_model_merged_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f317539516f689aca8a6b0b2e4ae6a28999b07bf6af700b6bdfa485aed4bb867
+size 127695

onnx/decoder_model_merged_q4f16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08edea158e32ec95c29cac14fa636ab0bf562eaed6efbd13a647d2e95dd36861
+size 312342528

onnx/embed_tokens.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fcae1b697f9e35d181c119d41f06a3d9153bf09b19280ef154b5f77fd64f29c
+size 268435815

onnx/embed_tokens_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291d72b491d3187f3cafbb0ec35c5f889360a044d7db815510eff0fabb2af371
+size 573

onnx/embed_tokens_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6936dd14d4e0fa29f4046159dfa5738363f020216ed39a2ed14d276d8d473aa6
+size 134217728

onnx/embed_tokens_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc6c3fab26502e87373f39e12da0f434256b83220aaa542689530853c55dd3
+size 440

onnx/embed_tokens_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff7054e7ccb91937cf032fb2fad0b459c168e60fbb379bc4c030ed17ef2165c
+size 268435456

onnx/embed_tokens_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f28d0ca5ec447470d42ca4ce0ac92a6f7fae90e91504601e63c138be8c9091
+size 447

onnx/embed_tokens_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff7054e7ccb91937cf032fb2fad0b459c168e60fbb379bc4c030ed17ef2165c
+size 268435456

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0170bb7f54d5dbb1b9a35b51f4b60b99feac3bb0753c3b8740fa2176c2763d1e
+size 123527

onnx/vision_encoder.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac5a4f96f8964b961d129f38c5549b57d25b170e896f3ce4a9567ddb500faaa
+size 376939520

onnx/vision_encoder_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c020610d1619939e98e0d355558dbc3a86f4e4f447747fabffb9fe77d8b7fb
+size 124811

onnx/vision_encoder_fp16.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7eb51d1edf6f2ac7e051abc56d602d2540345aeca8534d2bff20136ff3e591
+size 188469760

onnx/vision_encoder_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca4861376b1c409486a38237676754d0286d13b00e561bd113acebaaaddc56af
+size 146157

onnx/vision_encoder_q4.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c5dcb8282cdce1e0f4c80a05b8285cad3762e14acac0d241f83bc6b345d41b
+size 59982848

onnx/vision_encoder_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8650b9d3e2f80659b858c40b673f731a7371cf8ad3d8888e8f93b189a8f653c4
+size 161659

onnx/vision_encoder_quantized.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee54206551cff5e2e6ddda6da4f84677542b249258f1a70710ff43399c74a5c1
+size 109874176

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "processor_class": "Lfm2VlProcessor",
+  "image_processor_type": "Lfm2VlImageProcessor",
+  "data_format": "channels_first",
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "downsample_factor": 2,
+  "encoder_patch_size": 16,
+  "image_mean": [0.5, 0.5, 0.5],
+  "image_std": [0.5, 0.5, 0.5],
+  "max_image_tokens": 256,
+  "max_num_patches": 1024,
+  "max_pixels_tolerance": 2.0,
+  "max_tiles": 10,
+  "min_image_tokens": 64,
+  "min_tiles": 2,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "return_row_col_info": true,
+  "size": {
+    "height": 512,
+    "width": 512
+  },
+  "tile_size": 512,
+  "use_thumbnail": true
+}

processor_config.json

@@ -0,0 +1,39 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_image_splitting": true,
+    "do_normalize": true,
+    "do_pad": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "downsample_factor": 2,
+    "encoder_patch_size": 16,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Lfm2VlImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_image_tokens": 256,
+    "max_num_patches": 1024,
+    "max_pixels_tolerance": 2.0,
+    "max_tiles": 10,
+    "min_image_tokens": 64,
+    "min_tiles": 2,
+    "resample": 2,
+    "rescale_factor": 0.00392156862745098,
+    "return_row_col_info": true,
+    "size": {
+      "height": 512,
+      "width": 512
+    },
+    "tile_size": 512,
+    "use_thumbnail": true
+  },
+  "processor_class": "Lfm2VlProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [],
+  "image_end_token": "<|image_end|>",
+  "image_start_token": "<|image_start|>",
+  "image_thumbnail": "<|img_thumbnail|>",
+  "image_token": "<image>",
+  "is_local": true,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "image_end_token": "<|image_end|>",
+    "image_start_token": "<|image_start|>",
+    "image_token": "<image>"
+  },
+  "pad_token": "<|pad|>",
+  "processor_class": "Lfm2VlProcessor",
+  "return_token_type_ids": false,
+  "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 keep_past_thinking = keep_past_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_assistant_index=-1) -%}\n{%- if messages[0].role == \"system\" -%}\n    {%- if messages[0].content is defined -%}\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\\n\" if ns.system_prompt else \"\") + \"Today's date: \" + strftime_now(\"%Y-%m-%d\") + \"\\n\\nList of tools: \" + (tools | tojson) -%}\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 == \"assistant\" -%}\n        {%- set ns.last_assistant_index = loop.index0 -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n    {{- \"<|im_start|>\" + message.role + \"\\n\" -}}\n    {%- if message.role == \"assistant\" -%}\n        \n        {%- if message.thinking is defined and (keep_past_thinking or loop.index0 == ns.last_assistant_index) -%}\n            {{- \"<think>\" + message.thinking + \"</think>\" -}}\n        {%- endif -%}\n        {%- if message.tool_calls is defined -%}\n            {{- render_tool_calls(message.tool_calls) -}}\n        {%- endif -%}\n        {%- if message.content is defined -%}\n            {%- set content = parse_content(message.content) -%}\n            {%- if not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}\n                {%- if \"</think>\" in content -%}\n                    {%- set content = content.split(\"</think>\")[-1] | trim -%}\n                {%- endif -%}\n            {%- endif -%}\n            {{- content + (\"\" if (continue_final_message and loop.last) else \"<|im_end|>\\n\") -}}\n        {%- endif -%}\n        \n    {%- else %}\n        {%- if message.content is defined -%}\n            {{- parse_content(message.content) + \"<|im_end|>\\n\" -}}\n        {%- endif -%}\n    {%- endif %}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n    {{- \"<|im_start|>assistant\\n\" -}}\n{%- endif -%}"
+}