Upload folder using huggingface_hub

.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

LICENSE

@@ -0,0 +1,218 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work, excluding
+          those notices that do not pertain to any part of the Derivative
+          Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one of
+          the following places: within a NOTICE text file distributed as
+          part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and do
+          not modify the License. You may add Your own attribution notices
+          within Derivative Works that You distribute, alongside or as an
+          addendum to the NOTICE text from the Work, provided that such
+          additional attribution notices cannot be construed as modifying
+          the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 omni-research (Tarsier2-Recap-7b, original model)
+   Copyright 2026 viavicdev (MLX 4-bit conversion)
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+------------------------------------------------------------------------------
+
+NOTICE
+
+This repository, "Tarsier2-Recap-7b-MLX-4bit", is a derivative work: an MLX
+4-bit quantized conversion of "omni-research/Tarsier2-Recap-7b".
+
+All credit for the underlying model belongs to the original Tarsier2 authors
+(omni-research). This repository contributes only a format conversion:
+a weight-key remap into native Qwen2-VL layout followed by MLX 4-bit
+quantization. No model weights were retrained or otherwise altered in
+substance beyond quantization.
+
+Original model:  https://huggingface.co/omni-research/Tarsier2-Recap-7b
+Conversion by:   viavicdev

README.md

@@ -0,0 +1,131 @@
+---
+license: apache-2.0
+base_model: omni-research/Tarsier2-Recap-7b
+pipeline_tag: video-text-to-text
+library_name: mlx
+language:
+- en
+tags:
+- mlx
+- apple-silicon
+- video-captioning
+- qwen2-vl
+- tarsier
+---
+
+# Tarsier2-Recap-7b-MLX-4bit
+
+A 4-bit [MLX](https://github.com/ml-explore/mlx) conversion of
+[omni-research/Tarsier2-Recap-7b](https://huggingface.co/omni-research/Tarsier2-Recap-7b),
+so it runs natively and fast on Apple Silicon.
+
+Tarsier2 is one of the most detailed open video captioners available, but no
+official MLX build exists. This repo fills that gap: same model, quantized to
+4-bit, ~5.3 GB, running on the Mac GPU through MLX.
+
+- **Base model:** omni-research/Tarsier2-Recap-7b (Apache-2.0)
+- **Format:** MLX, 4-bit affine quantization (group size 64)
+- **Size on disk:** ~5.3 GB
+- **Underlying architecture:** Qwen2-VL 7B (see conversion notes below)
+- **Runs on:** Apple Silicon (tested on an M4 Pro, 24 GB unified memory)
+
+## Why this exists
+
+Tarsier2-Recap-7b produces unusually specific, grounded video descriptions —
+it reads small details (a sail number, an object in someone's hand,
+architectural features) rather than generic scene summaries. On Apple Silicon
+the only practical way to run a 7B vision-language model at usable speed is
+MLX 4-bit; the full bf16 weights via `transformers` on MPS are far too slow
+(hundreds of seconds per clip). This conversion gets it to roughly
+**7 seconds per short clip** on an M4 Pro.
+
+## Usage
+
+Run with [`mlx-vlm`](https://github.com/Blaizzy/mlx-vlm) (0.6.3 or newer).
+
+```python
+from mlx_vlm import load, generate
+from mlx_vlm.prompt_utils import apply_chat_template
+
+model, processor = load("viavicdev/Tarsier2-Recap-7b-MLX-4bit")
+
+# NOTE: feed video as a list of extracted frame images (see gotcha #1 below)
+frames = ["frame_00.jpg", "frame_01.jpg", "frame_02.jpg", "frame_03.jpg"]
+prompt = apply_chat_template(
+    processor, model.config,
+    "Describe this video in detail.",
+    num_images=len(frames),
+)
+out = generate(
+    model, processor, prompt,
+    image=frames,                 # note: image= (not images=)
+    max_tokens=300,
+    temperature=0.3,
+    repetition_penalty=1.3,       # see gotcha #3
+    repetition_context_size=40,
+)
+print(out)
+```
+
+### Gotchas (learned the hard way)
+
+1. **Feed frames as images, not a video file.** The `mlx-vlm` 0.6.3 video
+   decoder path is unreliable and can hallucinate. Extract frames with ffmpeg
+   and pass them as a list of images (`image=[...]` with
+   `num_images=N`). This delivers the real frames to the model.
+2. **The chat template is included** in this repo (`chat_template.json` /
+   `chat_template.jinja`). Some MLX repacks ship without it, which breaks
+   `apply_chat_template`.
+3. **Use a repetition penalty.** At 4-bit the model can occasionally loop.
+   `repetition_penalty=1.3`, `repetition_context_size=40`, `temperature=0.3`
+   keeps output clean. In testing, 1 of 22 clips degenerated without it; none with it.
+
+## How it was converted
+
+Tarsier2 ships as `TarsierForConditionalGeneration` with `model_type: llava`,
+but its text and vision towers **are Qwen2-VL weights under different key
+names**. The `mlx-vlm` llava handler does not support Qwen2-VL's mRoPE
+(it errors with `rope_scaling type only supports linear`); the `qwen2_vl`
+handler does. So the conversion is just a key-remap into native Qwen2-VL layout,
+followed by a standard MLX quantize.
+
+Only three key prefixes need remapping:
+
+```
+language_model.model.*    ->  model.*
+language_model.lm_head.*  ->  lm_head.*
+vision_tower.*            ->  visual.*
+```
+
+Then a flat `qwen2_vl` config is built from Tarsier's `text_config` +
+`vision_config` (preserving `rope_scaling: mrope`, the vision/image/video token
+ids, etc.), and the remapped weights are quantized:
+
+```bash
+mlx_vlm.convert --hf-path ./tarsier2-qwen2vl-hf -q --q-bits 4
+```
+
+This is a general pattern: **custom Qwen2-VL-based models (Tarsier and
+similar) that lack an official MLX or HF remote-code path can often be run on
+MLX via a key-remap**, as long as you route them through the `qwen2_vl` handler
+so mRoPE is respected.
+
+## Limitations
+
+- 4-bit quantization trades some fidelity for size/speed; for maximum quality
+  use the original bf16 weights on a CUDA machine.
+- English captioning model — it describes in English regardless of spoken
+  language in the clip.
+- Vision only (no audio). It captions what is *seen*, not heard.
+- Follows free-form description better than rigid output schemas; best used as
+  a captioner rather than a strict classifier.
+
+## License and attribution
+
+This conversion inherits the **Apache-2.0** license of the base model. All
+credit for the model itself goes to the Tarsier2 authors
+([omni-research/Tarsier2-Recap-7b](https://huggingface.co/omni-research/Tarsier2-Recap-7b)).
+This repository only provides a format conversion (weight key-remap + MLX 4-bit
+quantization) for the Apple Silicon community.
+
+If you cite Tarsier2, cite the original authors.

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,10 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}{% if (message['role'] != 'assistant') %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|>{{'<|image_pad|>' * content['num_vision_tokens']}}<|vision_end|>{% elif content['type'] == 'video' %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|>{{'<|image_pad|>' * content['num_vision_tokens']}}<|vision_end|>{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% elif (message['role'] == 'assistant') %}<|im_start|>{{ message['role'] }}
+{% generation %}{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|>{{'<|image_pad|>' * content['num_vision_tokens']}}<|vision_end|>{% elif content['type'] == 'video' %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|>{{'<|image_pad|>' * content['num_vision_tokens']}}<|vision_end|>{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% if not loop.last or not strip_final_eos %}<|im_end|>
+{% endif %}{% endif %}{% endgeneration %}{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

chat_template.json

@@ -0,0 +1,3 @@
+{
+    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,135 @@
+{
+    "architectures": [
+        "Qwen2VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "generation_config": {
+        "_from_model_config": true,
+        "bos_token_id": 151643,
+        "eos_token_id": 151645,
+        "transformers_version": "4.47.0",
+        "use_cache": true
+    },
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "image_token_id": 151655,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "model_type": "qwen2_vl",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "type": "mrope",
+        "mrope_section": [
+            16,
+            24,
+            24
+        ]
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "video_token_id": 151656,
+    "vision_config": {
+        "_attn_implementation_autoset": false,
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attn_implementation": "flash_attention_2",
+        "auto_map": {
+            "AutoConfig": "models--modeling_qwen2_vl_fast.Qwen2VLVisionConfig",
+            "AutoModel": "models--modeling_qwen2_vl_fast.Qwen2VisionTransformerPretrainedModel"
+        },
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "depth": 32,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": false,
+        "embed_dim": 1280,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "hidden_act": "quick_gelu",
+        "hidden_size": 3584,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "in_channels": 3,
+        "in_chans": 3,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "min_length": 0,
+        "mlp_ratio": 4,
+        "model_type": "qwen2_vl",
+        "no_repeat_ngram_size": 0,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_heads": 16,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": null,
+        "patch_size": 14,
+        "prefix": null,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "sep_token_id": null,
+        "spatial_merge_size": 2,
+        "spatial_patch_size": 14,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "temporal_patch_size": 2,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torch_dtype": null,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.47.0",
+  "use_cache": true
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a52da51d31b2561381a93fb9b63f8da3d9092260de469c83c3775043ebee76
+size 5329357921

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3254a4e13f2495304eccbf038b511cd8481abe340612cad5221878992fd7aa24
+size 306561371

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 2073600,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "TarsierProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 2073600,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

processor_config.json

@@ -0,0 +1,50 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen3VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_pixels": 2073600,
+    "merge_size": 2,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen2VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "fps": 2.0,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "max_frames": 768,
+    "max_pixels": 2073600,
+    "merge_size": 2,
+    "min_frames": 4,
+    "min_pixels": 3136,
+    "patch_size": 14,
+    "rescale_factor": 0.00392156862745098,
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8cce547abc110590d19c6b5b6e0c6a7b4c8d1012d78b9c42131bae7f494a02
+size 11420367

tokenizer_config.json

@@ -0,0 +1 @@
+{"add_prefix_space": false, "backend": "tokenizers", "bos_token": null, "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", "is_local": true, "local_files_only": false, "model_max_length": 32768, "pad_token": "<|endoftext|>", "padding_side": "left", "processor_class": "Qwen2VLProcessor", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null, "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"}