Add files using upload-large-folder tool

.eval_results/aime_2026.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: MathArena/aime_2026
+    task_id: MathArena/aime_2026
+  value: 95.5
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.eval_results/gpqa.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 89.5
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.eval_results/hle.yaml

@@ -0,0 +1,8 @@
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 31.6
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card
+  notes: text only

.eval_results/hmmt_feb_2026.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: MathArena/hmmt_feb_2026
+    task_id: MathArena/hmmt_feb_2026
+  value: 90.2
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.eval_results/mmmu_pro.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: MMMU/MMMU_Pro
+    task_id: mmmu_pro_standard_10_options
+  value: 74
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.eval_results/swe-bench_pro.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: ScaleAI/SWE-bench_Pro
+    task_id: SWE_Bench_Pro
+  value: 55.9
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.eval_results/swe-bench_verified.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 80.2
+  source:
+    url: https://huggingface.co/thinkingmachines/Inkling-Small
+    name: Model Card

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: thinkingmachines/Inkling-Small
+library_name: mlx
+tags:
+- mlx
+- vision
+- moe
+pipeline_tag: image-text-to-text
+---
+
+# ToPo-ToPo/Inkling-Small-mlx-2bit
+
+MLX **2bit** conversion of [`thinkingmachines/Inkling-Small`](https://huggingface.co/thinkingmachines/Inkling-Small)
+for Apple Silicon (mlx-vlm). 276B total / 12B active sparse MoE (42 layers, 256 routed experts top-6 + 2 shared),
+text + image + audio in, text out.
+
+See also: [`ToPo-ToPo/Inkling-Small-mlx-4bit`](https://huggingface.co/ToPo-ToPo/Inkling-Small-mlx-4bit).
+
+## Provenance (self-converted from official weights)
+- Source: [`thinkingmachines/Inkling-Small`](https://huggingface.co/thinkingmachines/Inkling-Small) (license: apache-2.0, bf16, 531.9 GB)
+- Tool: `mlx-vlm 0.6.7` — `mlx_vlm.convert --hf-path <staged> --mlx-path . -q --q-bits 2 --q-group-size 64`
+- Effective: **2.506 bits/weight** (77 GiB on disk, ~83.5 GB peak RSS at inference)
+
+## Config translation (already applied here)
+
+The official `config.json` cannot be loaded by `mlx-vlm` as published — its schema uses different key names
+than `mlx_vlm.models.inkling` expects. This repo ships the translated config, so no action is needed:
+
+| Key | Official | Here |
+| --- | --- | --- |
+| `model_type` | `inkling_mm_model` | `inkling` |
+| `text_config.intermediate_size` | 2048 (expert width) | 16384 (dense width) |
+| `text_config.moe_intermediate_size` | — (was `intermediate_size`) | 2048 |
+| `vision_config.text_hidden_size` | `decoder_dmodel` | 4096 |
+| `audio_config.text_hidden_size` | `decoder_dmodel` | 4096 |
+| `vision_config.num_channels` | `n_channels` | 3 |
+| `tokenizer_config.pad_token` / `eos_token` | unset | `<\|endoftext\|>` / `<\|content_model_end_sampling\|>` |
+
+`image_token_id` / `audio_token_id` are left unset so that mlx-vlm's defaults (200054 / 200053) apply —
+those are the placeholders `InklingProcessor` actually emits.
+
+## Loader shim (required)
+
+`mlx-vlm` 0.6.7 and 0.6.8 need two patches at runtime for any Inkling checkpoint. Apply them before `load()`:
+
+```python
+from mlx_vlm.models import inkling
+from mlx_vlm.models.inkling import config as inkling_config
+from mlx_vlm import prompt_utils
+
+# 1. models/inkling does not re-export its sub-config classes, which the generic
+#    loader fetches with getattr -> AttributeError on load.
+for name in ("TextConfig", "VisionConfig", "AudioConfig"):
+    setattr(inkling, name, getattr(inkling_config, name))
+
+# 2. prompt_utils.MODEL_CONFIG has no "inkling" entry, so apply_chat_template treats
+#    the model as text-only and drops image/audio parts.
+prompt_utils.MODEL_CONFIG.setdefault("inkling", prompt_utils.MessageFormat.LIST_WITH_IMAGE_FIRST)
+```
+
+When serving over `mlx_vlm.server`, also add Inkling's structural tokens to
+`mlx_vlm.server.responses_state._CONTENT_MARKERS` (`<|message_model|>`, `<|content_text|>`,
+`<|end_message|>`) and set `MLX_VLM_THINKING_START_TOKEN=<|content_thinking|>` /
+`MLX_VLM_THINKING_END_TOKEN=<|end_message|>`, so the reasoning channel and those markers do not
+end up in `content`.
+
+## Reasoning effort
+
+The chat template always injects a `Thinking effort level:` system message (default **0.9**). Control it
+with the OpenAI-compatible `reasoning_effort` — `"none"` / `"minimal"` / `"low"` / `"medium"` / `"high"` /
+`"max"`, or a float in `[0.0, 0.99]`. `"none"` disables thinking entirely.
+
+## Usage
+
+```python
+from mlx_vlm import load, generate
+model, processor = load("ToPo-ToPo/Inkling-Small-mlx-2bit")  # apply the shim above first
+```
+
+The first load reads 77 GiB, so allow a few minutes and raise any client-side startup timeouts accordingly.

chat_template.jinja

@@ -0,0 +1,129 @@
+{%- set effort_map = {"none": 0.0, "minimal": 0.1, "low": 0.2, "medium": 0.7, "high": 0.9, "max": 0.99} -%}
+{%- set role_token = {"user": "<|message_user|>", "assistant": "<|message_model|>", "system": "<|message_system|>", "tool": "<|message_tool|>"} -%}
+
+{%- macro emit_thinking_effort() -%}
+    {%- set eff = reasoning_effort if reasoning_effort is defined and reasoning_effort is not none else 0.9 -%}
+    {%- if eff is string -%}
+        {%- set key = eff | trim -%}
+        {%- if key not in effort_map -%}
+            {{- raise_exception("Unknown reasoning_effort: " ~ eff) -}}
+        {%- endif -%}
+        {%- set num = effort_map[key] -%}
+    {%- else -%}
+        {%- set num = eff | float -%}
+    {%- endif -%}
+    {%- if num < 0.0 or num > 0.99 -%}
+        {{- raise_exception("reasoning_effort must be in [0.0, 0.99]") -}}
+    {%- endif -%}
+    {{- "<|message_system|><|content_text|>Thinking effort level: " -}}
+    {%- if num == 0.0 -%}0{%- else -%}{{ num }}{%- endif -%}
+    {{- "<|end_message|>" -}}
+{%- endmacro -%}
+
+{%- if tools -%}
+    {%- set tool_state = namespace(specs=[]) -%}
+    {%- for tool in tools -%}
+        {%- set fn = tool.function if tool.function is defined else tool -%}
+        {%- set spec = {
+            "description": (fn.description if fn.description is defined and fn.description else ""),
+            "name": fn.name,
+            "parameters": (fn.parameters if fn.parameters is defined and fn.parameters else {}),
+            "type": (tool.type if tool.type is defined and tool.type else "function"),
+        } -%}
+        {%- set tool_state.specs = tool_state.specs + [spec] -%}
+    {%- endfor -%}
+    {{- "<|message_system|>tool_declare<|content_xml|>" -}}
+    {{- tool_state.specs | tojson(sort_keys=true, separators=(",", ":")) -}}
+    {{- "<|end_message|>" -}}
+{%- endif -%}
+
+{%- set state = namespace(effort_emitted=false) -%}
+{%- for message in messages -%}
+    {%- if message.role not in role_token -%}
+        {{- raise_exception("Unknown message role: " ~ message.role) -}}
+    {%- endif -%}
+    {%- if not state.effort_emitted and message.role != "system" -%}
+        {{- emit_thinking_effort() -}}
+        {%- set state.effort_emitted = true -%}
+    {%- endif -%}
+
+    {%- set rtok = role_token[message.role] -%}
+
+    {%- if message.role == "tool" -%}
+        {%- set tool_name_state = namespace(name="") -%}
+        {%- if message.name is defined and message.name -%}
+            {%- set tool_name_state.name = message.name -%}
+        {%- elif message.tool_call_id is defined and message.tool_call_id -%}
+            {%- for prev in messages -%}
+                {%- if prev.role == "assistant" and prev.tool_calls -%}
+                    {%- for tc in prev.tool_calls -%}
+                        {%- if tc.id is defined and tc.id == message.tool_call_id and tc.function.name is defined -%}
+                            {%- set tool_name_state.name = tc.function.name -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {{- rtok -}}
+        {%- if tool_name_state.name -%}{{- tool_name_state.name -}}{%- endif -%}
+        {{- "<|content_text|>" -}}
+        {%- if message.content is string -%}{{- message.content -}}{%- endif -%}
+        {{- "<|end_message|>" -}}
+
+    {%- else -%}
+        {%- if message.role == "assistant" and message.reasoning_content is defined and message.reasoning_content -%}
+            {{- "<|message_model|><|content_thinking|>" ~ message.reasoning_content ~ "<|end_message|>" -}}
+        {%- endif -%}
+
+        {%- if message.content is string -%}
+            {{- rtok ~ "<|content_text|>" ~ message.content ~ "<|end_message|>" -}}
+        {%- elif message.content -%}
+            {%- for part in message.content -%}
+                {%- if part is string -%}
+                    {{- rtok ~ "<|content_text|>" ~ part ~ "<|end_message|>" -}}
+                {%- elif part.type is not defined or part.type in ("text", "input_text") -%}
+                    {%- set text_part = (part.text if part.text is defined and part.text is string else "") -%}
+                    {{- rtok ~ "<|content_text|>" ~ text_part ~ "<|end_message|>" -}}
+                {%- elif part.type in ("image", "input_image", "image_url") -%}
+                    {{- rtok ~ "<|content_image|><|unused_200054|><|end_message|>" -}}
+                {%- elif part.type in ("audio", "input_audio", "audio_url") -%}
+                    {{- rtok ~ "<|content_audio_input|><|unused_200053|><|audio_end|><|end_message|>" -}}
+                {%- else -%}
+                    {{- raise_exception("Unsupported content part type: " ~ part.type) -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+
+        {%- if message.role == "assistant" and message.tool_calls -%}
+            {%- for tc in message.tool_calls -%}
+                {%- set fn = tc.function -%}
+                {%- if fn.name is not defined or fn.name is not string -%}
+                    {{- raise_exception("tool call function name must be a string") -}}
+                {%- endif -%}
+                {%- set args = fn.arguments if fn.arguments is defined and fn.arguments else {} -%}
+                {%- if args is string -%}
+                    {{- raise_exception("tool call arguments must be a parsed object, not a JSON string; canonicalize upstream") -}}
+                {%- endif -%}
+                {%- if args is not mapping -%}
+                    {{- raise_exception("tool call arguments must be an object") -}}
+                {%- endif -%}
+                {{- "<|message_model|>" ~ fn.name ~ "<|content_invoke_tool_json|>" -}}
+                {{- '{"name":' ~ (fn.name | tojson(sort_keys=true, separators=(",", ":"))) ~ ',"args":' -}}
+                {{- (args | tojson(sort_keys=true, separators=(",", ":"))) -}}
+                {{- "}<|end_message|>" -}}
+            {%- endfor -%}
+        {%- endif -%}
+
+        {%- if message.role == "assistant" -%}
+            {{- "<|content_model_end_sampling|>" -}}
+        {%- endif -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if not state.effort_emitted -%}
+    {{- emit_thinking_effort() -}}
+{%- endif -%}
+
+{%- if add_generation_prompt -%}
+    {{- "<|message_model|>" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,124 @@
+{
+    "architectures": [
+        "InklingForConditionalGeneration"
+    ],
+    "audio_config": {
+        "n_mel_bins": 80,
+        "mel_vocab_size": 16,
+        "bias": false,
+        "dmel_min_value": -7.0,
+        "dmel_max_value": 2.0,
+        "use_audio_norm": true,
+        "audio_mode": "dmel",
+        "text_hidden_size": 4096
+    },
+    "eos_token_id": 200006,
+    "model_type": "inkling",
+    "mtp_config": {
+        "num_nextn_predict_layers": 8,
+        "chain_hidden_post_norm": false,
+        "local_layer_ids": [
+            0,
+            2,
+            4,
+            5,
+            6,
+            7
+        ]
+    },
+    "quantization": {
+        "group_size": 64,
+        "bits": 2,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 2,
+        "mode": "affine"
+    },
+    "text_config": {
+        "model_max_length": 1048576,
+        "torch_dtype": "bfloat16",
+        "hidden_size": 4096,
+        "num_hidden_layers": 42,
+        "vocab_size": 201024,
+        "num_attention_heads": 32,
+        "num_key_value_heads": 8,
+        "head_dim": 128,
+        "d_rel": 16,
+        "rel_extent": 1024,
+        "q_bias": false,
+        "o_bias": false,
+        "log_scaling_n_floor": 128000,
+        "log_scaling_alpha": 0.1,
+        "rms_norm_eps": 1e-06,
+        "use_embed_norm": true,
+        "local_layer_ids": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            6,
+            7,
+            8,
+            9,
+            10,
+            12,
+            13,
+            14,
+            15,
+            16,
+            18,
+            19,
+            20,
+            21,
+            22,
+            24,
+            25,
+            26,
+            27,
+            28,
+            30,
+            31,
+            32,
+            33,
+            34,
+            36,
+            37,
+            38,
+            39,
+            40
+        ],
+        "dense_mlp_idx": 2,
+        "use_sconv": true,
+        "sconv_kernel_size": 4,
+        "unpadded_vocab_size": 200058,
+        "logits_mup_width_multiplier": 16.0,
+        "final_logit_softcapping": null,
+        "swa_head_dim": 128,
+        "swa_num_attention_heads": 32,
+        "swa_num_key_value_heads": 8,
+        "sliding_window_size": 512,
+        "n_routed_experts": 256,
+        "num_experts_per_tok": 6,
+        "n_shared_experts": 2,
+        "shared_expert_sink": true,
+        "intermediate_size": 16384,
+        "route_scale": 8.0,
+        "use_gate_bias": true,
+        "gate_activation": "sigmoid",
+        "norm_after_topk": true,
+        "use_global_scale": true,
+        "moe_intermediate_size": 2048
+    },
+    "vision_config": {
+        "vision_encoder_type": "hmlp",
+        "patch_size": 40,
+        "temporal_patch_size": 2,
+        "n_layers": 4,
+        "use_vision_norm": true,
+        "num_channels": 3,
+        "text_hidden_size": 4096
+    }
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27171f0f989f1a71f35c7d8967f8e5f6506608eb46e2326911f0d52b11f97ff5
+size 5187900962

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837e7c88b8f4043486cd9b69d811a3753ef036ea7fe3d1309a21dd4c5678abf5
+size 5365071335

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dced781d910d705a8ee86b11c7c49d1932a82cb2ff90af7105b618e0ba131c19
+size 4859909583

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f62312f7e5dd3c8f803e1134fc8371b6406147b6b22442d4286a2402007b060
+size 5365071471

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4918dbdb9ca2add617b0c61fa579c80f3999f101c324e9919246831ac5365b6f
+size 4859909727

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295e1bcd71c1f2d308c8a7ba14010e0a52e5416563835a15899fc401f7753f79
+size 5365055039

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812490c0da651ff7dac6d62f1b3c98c29c7e86dc3bc453af998b02c3a2a3d68f
+size 4859926156

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aef9a454632bd934919ab64e0b3fbd4bd60df94e41b63e9b805827664cff6ca
+size 5365055095

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f63ef9294524befb334d8a4c2ebee35ba0a5e1d02561706d95a6fd478285f5
+size 4859926148

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81177d8a971d5bedad9c17ad6a55213a2210cf06dcc119d39dd3960371f58bf8
+size 5365055043

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90b808b6f4add8fa09db3a73d6c1b8058890f3c2e4a015184607de77b695480f
+size 4859926158

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffa3548e85648edd71660902223fdbae20c2a99b1b9a3a022654af3ea1ed89a
+size 5365055103

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108804d405ced5048a9d0932e554e9ee6a208c3d5070eefc28e1acb1a0e7d8b5
+size 4859909783

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b8834eb749e562dcbd18f4c51f0bfa1cd7f5eed90b536b45bf54eaf3c0789c
+size 5365071424

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b38c9613579e1c87572c858d52b23f8164eedb583da034b10d18c0e28afbe78
+size 4859909735

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75b84c0d634641218f19928945dfeee90e6eb9ab94d0527f977beb411ef47c60
+size 5365071474

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d738dee26b15bd4fcd42f19ef4f73554f8820de2e118adca4448c70be4ccd11
+size 478896590

processor_config.json

@@ -0,0 +1,47 @@
+{
+  "audio_bos_token": "<|content_audio_input|>",
+  "audio_token": "<|unused_200053|>",
+  "dmel_max_value": 2.0,
+  "dmel_min_value": -7.0,
+  "feature_extractor": {
+    "audio_token_duration_s": 0.05,
+    "feature_extractor_type": "InklingFeatureExtractor",
+    "feature_size": 80,
+    "hop_length": 800,
+    "n_fft": 1600,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": true,
+    "sampling_rate": 16000,
+    "window_size": 1600,
+    "window_size_multiplier": 2.0
+  },
+  "image_bos_token": "<|content_image|>",
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "InklingImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "rescale_image_max_upscaled_long_edge": 2048,
+    "size": {
+      "height": 40,
+      "width": 40
+    }
+  },
+  "image_token": "<|unused_200054|>",
+  "num_dmel_bins": 16,
+  "processor_class": "InklingProcessor"
+}

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|message_user|>",
+    "<|message_model|>",
+    "<|message_system|>",
+    "<|message_tool|>",
+    "<|content_text|>",
+    "<|content_image|>",
+    "<|content_model_end_sampling|>",
+    "<|content_thinking|>",
+    "<|end_message|>",
+    "<|content_audio_input|>",
+    "<|content_tool_error|>",
+    "<|audio|>",
+    "<|content_xml|>",
+    "<|begin_of_text|>",
+    "<|audio_end|>",
+    "<|content_invoke_tool_json|>",
+    "<|content_invoke_tool_text|>"
+  ]
+}

tiktoken/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc253fd2b702f7a6da7105eaa8f3463b2f1247e83614f23e5323b921088bed2a
+size 3615874

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c470271fb7649eef922e660e757b5f076e2a94adc20df7fad7df85c46bc48eac
+size 27875796

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "audio": "<|audio|>",
+  "audio_end": "<|audio_end|>",
+  "backend": "tokenizers",
+  "begin_of_text": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "content_audio_input": "<|content_audio_input|>",
+  "content_image": "<|content_image|>",
+  "content_invoke_tool_json": "<|content_invoke_tool_json|>",
+  "content_invoke_tool_text": "<|content_invoke_tool_text|>",
+  "content_model_end_sampling": "<|content_model_end_sampling|>",
+  "content_text": "<|content_text|>",
+  "content_thinking": "<|content_thinking|>",
+  "content_tool_error": "<|content_tool_error|>",
+  "content_xml": "<|content_xml|>",
+  "end_message": "<|end_message|>",
+  "endoftext": "<|endoftext|>",
+  "eos_token": "<|content_model_end_sampling|>",
+  "fix_mistral_regex": false,
+  "is_local": true,
+  "local_files_only": false,
+  "message_model": "<|message_model|>",
+  "message_system": "<|message_system|>",
+  "message_tool": "<|message_tool|>",
+  "message_user": "<|message_user|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio": "<|audio|>",
+    "audio_end": "<|audio_end|>",
+    "begin_of_text": "<|begin_of_text|>",
+    "content_audio_input": "<|content_audio_input|>",
+    "content_image": "<|content_image|>",
+    "content_invoke_tool_json": "<|content_invoke_tool_json|>",
+    "content_invoke_tool_text": "<|content_invoke_tool_text|>",
+    "content_model_end_sampling": "<|content_model_end_sampling|>",
+    "content_text": "<|content_text|>",
+    "content_thinking": "<|content_thinking|>",
+    "content_tool_error": "<|content_tool_error|>",
+    "content_xml": "<|content_xml|>",
+    "end_message": "<|end_message|>",
+    "endoftext": "<|endoftext|>",
+    "message_model": "<|message_model|>",
+    "message_system": "<|message_system|>",
+    "message_tool": "<|message_tool|>",
+    "message_user": "<|message_user|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "processor_class": "InklingProcessor",
+  "tokenizer_class": "TokenizersBackend"
+}