Upload karpo-decision-9B

.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 +1,43 @@
+MachinePulse Community License
+
+Copyright (c) 2026 MachinePulse Limited
+
+Karpo Decision (karpo-decision-9B) is a modified version of Qwen3.5-9B, developed by the Qwen team at Alibaba Cloud and licensed under the Apache License, Version 2.0. Qwen3.5 and any other third-party components included with the Software remain subject to their original licenses, and nothing in this license limits any rights granted under those licenses. This license applies only to the modifications, model weights, and other contributions made by MachinePulse Limited. The inference code at https://github.com/machinepulse-ai/karpo-decision is licensed separately under the Apache License, Version 2.0, and is not part of the Software.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of the Karpo Decision model, including its weights and associated files and documentation (the "Software"), to deal in the Software, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or provide copies of the Software, including for Commercial Use, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+1. The above copyright notice and this permission notice, together with the NOTICE file and a copy of the Apache License, Version 2.0 under which Qwen3.5 is licensed, shall be included in all copies or substantial portions of the Software.
+
+2. If the Software (or any Derivative Work thereof) is used in Production for any Commercial Use by an entity whose Annual Revenue exceeds 10,000,000 US dollars (or the equivalent in other currencies), whether the Software or Derivative Work is operated by that entity or by a third party on its behalf, such entity shall obtain a separate written commercial agreement from MachinePulse Limited by contacting contact@machinepulse.ai with the subject line "Karpo Decision licensing: commercial agreement request".
+
+3. Annual Revenue is measured over the preceding twelve (12) months and reassessed at the end of each fiscal quarter. An entity that first exceeds the threshold in Section 2 while already using the Software in Production may continue such use for ninety (90) days after the end of the quarter in which the threshold was exceeded, during which it shall request a commercial agreement. If no commercial agreement is in place at the end of that period, the entity's right to use the Software in Production for Commercial Use terminates.
+
+4. If the Software (or any Derivative Work thereof) is used for any External Commercial Use, you shall prominently display "Powered by karpo-decision (MachinePulse)" on a related website, user interface, about page, or product documentation, together with a link to https://huggingface.co/MachinePulseAI/karpo-decision-9B where the medium allows a link. This attribution is not required for any use that is not External Commercial Use (Section 8(b)).
+
+5. If you create, distribute, or otherwise make available any Derivative Work:
+
+   a. you shall include a copy of this license and the NOTICE file with such Derivative Work;
+
+   b. you shall distribute such Derivative Work only under the terms of this license, and any recipient or user of such Derivative Work shall be bound by Sections 2 through 4 as a condition of its use; and
+
+   c. Sections 2 through 4 shall apply to any use of a Derivative Work, regardless of whether such Derivative Work was created, modified, or hosted by you or by a third party.
+
+6. This license does not grant permission to use the trade names, trademarks, service marks, or product names of MachinePulse Limited, including "MachinePulse" and "Karpo", except as required for the attribution in Section 4 and for reasonable and customary use in describing the origin of the Software. The attribution in Section 4 does not imply endorsement by, sponsorship by, or affiliation with MachinePulse Limited.
+
+7. Except as provided in Section 3, if you breach any condition of this license and do not cure the breach within thirty (30) days after receiving written notice of it from MachinePulse Limited, your rights under this license terminate automatically.
+
+8. For purposes of this license:
+
+   a. "Commercial Use" means any use of the Software or any Derivative Work that is primarily intended for commercial advantage or monetary compensation, including without limitation: (i) offering products or services to third parties for a fee which utilize, incorporate, or rely on the Software or its Derivative Works; (ii) the commercial use of APIs provided by or for the Software or its Derivative Works, whether in a cloud-based, hosted, or other similar environment; and (iii) the use of the Software or its Derivative Works in the internal operations of a for-profit entity.
+
+   b. "External Commercial Use" means any Commercial Use in which the Software or a Derivative Work is used in, or to provide, a product or service made available to third parties, whether offered for a fee or free of charge, including without limitation public or third-party APIs, hosted services, and products that embed the Software or a Derivative Work. External Commercial Use does not include internal operations or internal tools, evaluation, testing, benchmarking, or research, or a pilot lasting no more than ninety (90) days that does not serve paying customers.
+
+   c. "Production" means any deployment of the Software or a Derivative Work that serves end users, customers, or employees, or supports business operations, whether offered for a fee or free of charge, including internal tools and customer-facing services. Production does not include evaluation, testing, benchmarking, or research, or a pilot lasting no more than ninety (90) days that does not serve paying customers.
+
+   d. "Annual Revenue" means the aggregate, consolidated gross revenue of an entity and all of its Affiliates over the preceding twelve (12) months.
+
+   e. "Affiliate" means any entity that directly or indirectly controls, is controlled by, or is under common control with another entity, where "control" means ownership of more than fifty percent (50%) of the voting interests of an entity or the power to direct its management and policies.
+
+   f. "Derivative Work" means any modification of, or work based on, the Software, including without limitation fine-tuned, instruction-tuned, merged, quantized, or pruned versions of its model weights, and any model distilled using its model weights. A model trained only on outputs generated by the Software or a Derivative Work, and which does not incorporate any of their model weights, is not a Derivative Work.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

NOTICE

@@ -0,0 +1,21 @@
+Karpo Decision (karpo-decision-9B)
+Developed by MachinePulse Limited
+https://machinepulse.ai
+https://karpo.ai (Karpo, a MachinePulse product)
+https://huggingface.co/MachinePulseAI/karpo-decision-9B
+
+karpo-decision-9B is a modified version of Qwen3.5-9B (Qwen/Qwen3.5-9B),
+developed by the Qwen team at Alibaba Cloud and licensed under the Apache License,
+Version 2.0.
+MachinePulse fine-tuned the decoder weights for decision modeling and added a linear
+readout over the options. MachinePulse contributions are subject to the
+MachinePulse Community License in LICENSE.
+
+A copy of the Apache License, Version 2.0, under which Qwen3.5 is licensed, is
+included in licenses/Qwen3.5-LICENSE. Qwen3.5 and other third-party components remain
+subject to their original licenses.
+
+The inference code (https://github.com/machinepulse-ai/karpo-decision) is licensed
+separately under the Apache License, Version 2.0.
+
+Licensing: contact@machinepulse.ai

README.md

@@ -0,0 +1,147 @@
+---
+license: other
+license_name: machinepulse-community
+license_link: https://huggingface.co/MachinePulseAI/karpo-decision-9B/blob/main/LICENSE
+library_name: transformers
+base_model: Qwen/Qwen3.5-9B
+base_model_relation: finetune
+pipeline_tag: text-classification
+tags:
+  - decision-model
+  - decision-index
+  - system-one
+  - qwen3_5
+---
+
+# Karpo Decision 9B
+
+<p>
+  <a href="https://github.com/machinepulse-ai/karpo-decision"><img alt="GitHub" src="https://img.shields.io/badge/GitHub-machinepulse--ai%2Fkarpo--decision-181717?style=flat-square&logo=github&logoColor=white"></a>
+  <a href="https://huggingface.co/MachinePulseAI/karpo-decision-31B"><img alt="Karpo Decision 31B: Decision Index #1" src="https://img.shields.io/badge/Karpo_Decision_31B-Decision_Index_%231-FFD21E?style=flat-square"></a>
+  <a href="https://huggingface.co/MachinePulseAI/karpo-decision-9B/blob/main/LICENSE"><img alt="License: MachinePulse Community License" src="https://img.shields.io/badge/License-MachinePulse_Community-4b5563?style=flat-square"></a>
+</p>
+
+A decision model of the Karpo Decision family: given a state (a web page, a document, a conversation: any text or
+JSON) and typed questions about it, it returns a probability for every option of every question in one forward pass,
+without generating text. Fine-tuned from [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B), with a linear readout over
+the options.
+
+- **Parameters:** 8.4B in bf16, plus a 255 × 4,096 readout in fp32
+- **Questions:** `choice` (up to 255 options), `noul` (true or false), `score` (a level on a scale)
+- **Inputs:** text or JSON, and a screenshot at `state.viewport_screenshot`
+- **Context:** 32,768 tokens per sequence; a longer request is split by questions, each part with the full state
+- **Interfaces:** a Python API and an HTTP server in the System One format (`POST /v1/systemone`)
+- **Licence:** [MachinePulse Community License](LICENSE): commercial use is allowed; commercial products and services
+  offered to third parties must show "Powered by karpo-decision (MachinePulse)"; production use for commercial
+  purposes by an entity whose annual revenue, with its affiliates, exceeds US$10M needs a commercial agreement
+
+## The Karpo Decision family
+
+| Model | Base | Parameters |
+|---|---|---|
+| [karpo-decision-31B](https://huggingface.co/MachinePulseAI/karpo-decision-31B) | Gemma 4 31B | 31.3B |
+| [karpo-decision-12B](https://huggingface.co/MachinePulseAI/karpo-decision-12B) | Gemma 4 12B | 12.0B |
+| **karpo-decision-9B** | Qwen3.5 9B | 8.4B |
+| [karpo-decision-4B](https://huggingface.co/MachinePulseAI/karpo-decision-4B) | Qwen3.5 4B | 4.5B |
+| [karpo-decision-2B](https://huggingface.co/MachinePulseAI/karpo-decision-2B) | Qwen3.5 2B | 2.2B |
+| [karpo-decision-0.8B](https://huggingface.co/MachinePulseAI/karpo-decision-0.8B) | Qwen3.5 0.8B | 0.85B |
+
+The family's largest model, [karpo-decision-31B](https://huggingface.co/MachinePulseAI/karpo-decision-31B), is ranked #1 on the
+[Decision Index](https://huggingface.co/spaces/multimodalart/jev-decision-index), with the highest Full score, 73.9, on
+the maintainers' private tests (edition 0.4.1, board of 12 November 2026, 300 entries); its public index is 75.0.
+
+## How it works
+
+- **A readout, not generation.** Every option is labelled with an option code. At the readout point that ends each
+  question, a linear readout scores 255 option codes and a softmax over the question's own options gives the
+  probabilities. Nothing is decoded, so the answer is always one of the options.
+- **Many questions, one forward pass.** A request is one state and any number of questions, encoded as one sequence:
+  the list of questions, the state, then each question again with its options and a readout point.
+- **Hybrid attention.** The full-attention layers read the whole sequence in both directions; the linear-attention
+  layers read it in order, so the questions come before the state.
+
+The question-list-first layout follows [FlexDM](https://github.com/1000luca/FlexDM) and
+[jev-brain](https://github.com/wcole3/jev-brain).
+
+## Use
+
+Inference code: [github.com/machinepulse-ai/karpo-decision](https://github.com/machinepulse-ai/karpo-decision), with the `qwen` extra. Python 3.12 or later and one GPU; the weights
+take 16.8 GB, long requests more. Loading the checkpoint as a plain chat model does not reproduce its answers.
+
+```bash
+pip install "karpo-decision[qwen] @ git+https://github.com/machinepulse-ai/karpo-decision"
+```
+
+```python
+from huggingface_hub import snapshot_download
+from karpo_decision.decider import Decider
+
+path = snapshot_download("MachinePulseAI/karpo-decision-9B")
+decider = Decider.from_pretrained(path, device="cuda")
+response = decider.decide({
+    "state": "Order 1182: the customer asks to return a blender bought 45 days ago. Policy: returns within 30 days.",
+    "questions": {
+        "eligible": {"type": "noul", "instructions": "Is the return eligible under the policy?"},
+        "action": {"type": "choice", "instructions": "What should the agent do?",
+                   "criteria": {"refund": "Issue a full refund", "decline": "Politely decline the return",
+                                "escalate": "Escalate to a supervisor"}},
+    },
+})
+print(response["answers"])
+# {"eligible": {"type": "noul", "noul": P(true)},
+#  "action": {"type": "choice", "choice": <key>, "probabilities": {<key>: p, ...}, "confidence": c}}
+```
+
+A screenshot goes in the state at `viewport_screenshot`, as `{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}}`.
+
+HTTP server (`POST /v1/systemone`, `GET /healthz`):
+
+```bash
+CKPT=$(python -c 'from huggingface_hub import snapshot_download; print(snapshot_download("MachinePulseAI/karpo-decision-9B"))')
+torchrun --standalone --nproc_per_node 1 -m karpo_decision.serve.server --checkpoint "$CKPT" --port 18440
+```
+
+[Decision Index](https://github.com/apolinario/decision-index) kit, installed separately:
+
+```bash
+pip install "decision-index @ git+https://github.com/apolinario/decision-index"
+python -m decision_index run --engine karpo_decision.serve.engine:DecisionIndexEngine \
+    --option checkpoint="$CKPT" --out runs/karpo-decision-9B
+```
+
+## Lineage
+
+[Qwen/Qwen3.5-9B-Base](https://huggingface.co/Qwen/Qwen3.5-9B-Base) → [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B)
+→ **karpo-decision-9B** (fine-tuned)
+
+## Limitations
+
+- Images: a screenshot is read through the base model's vision tower; image inputs were not evaluated.
+- Not a chat or text-generation model; generation was not evaluated.
+- A question that does not fit in 32,768 tokens with its state is refused, never truncated.
+- It always picks one of the given options.
+
+## Licence
+
+The weights and model files are licensed under the [MachinePulse Community License](LICENSE); this summary is for
+convenience and the LICENSE governs. Commercial use is allowed. Commercial products and services offered to third
+parties, paid or free, must carry the attribution below; internal use and internal tools, evaluation, testing,
+benchmarking, research, and pilots of up to 90 days that serve no paying customers need none. Production use for
+commercial purposes by an entity whose annual revenue, with its affiliates, exceeds US$10M needs a separate commercial
+agreement: write to contact@machinepulse.ai with the subject line "Karpo Decision licensing: commercial agreement
+request". Models fine-tuned, merged, quantized, pruned or distilled from these weights stay under the same licence;
+a model trained only on this model's outputs does not.
+
+karpo-decision-9B is a modified version of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) ([Apache-2.0](https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE)):
+decoder weights fine-tuned, readout added. Qwen3.5 stays under its own licence, a copy of which is in [licenses/Qwen3.5-LICENSE](licenses/Qwen3.5-LICENSE); see [NOTICE](NOTICE).
+
+The inference code ([github.com/machinepulse-ai/karpo-decision](https://github.com/machinepulse-ai/karpo-decision)) is licensed under Apache-2.0.
+
+### Attribution
+
+Commercial products and services offered to third parties that use this model or a derivative must show, on a related
+website, user interface, about page or product documentation:
+
+> Powered by karpo-decision (MachinePulse)
+
+with a link to <https://huggingface.co/MachinePulseAI/karpo-decision-9B> where the medium allows one.

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.21.0",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "axial"
+    },
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

decision_config.json

@@ -0,0 +1,529 @@
+{
+ "template": "karpo-joint-preview-v1",
+ "codes": [
+  "A",
+  "B",
+  "C",
+  "D",
+  "E",
+  "F",
+  "G",
+  "H",
+  "I",
+  "J",
+  "K",
+  "L",
+  "M",
+  "N",
+  "O",
+  "P",
+  "Q",
+  "R",
+  "S",
+  "T",
+  "U",
+  "V",
+  "W",
+  "X",
+  "Y",
+  "Z",
+  "AA",
+  "AB",
+  "AC",
+  "AD",
+  "AE",
+  "AF",
+  "AG",
+  "AH",
+  "AI",
+  "AJ",
+  "AK",
+  "AL",
+  "AM",
+  "AN",
+  "AO",
+  "AP",
+  "AQ",
+  "AR",
+  "AS",
+  "AT",
+  "AU",
+  "AV",
+  "AW",
+  "AX",
+  "AY",
+  "AZ",
+  "BA",
+  "BB",
+  "BC",
+  "BD",
+  "BE",
+  "BF",
+  "BG",
+  "BH",
+  "BI",
+  "BJ",
+  "BK",
+  "BL",
+  "BM",
+  "BN",
+  "BO",
+  "BP",
+  "BR",
+  "BS",
+  "BT",
+  "BU",
+  "BV",
+  "BW",
+  "BX",
+  "BY",
+  "CA",
+  "CB",
+  "CC",
+  "CD",
+  "CE",
+  "CF",
+  "CG",
+  "CH",
+  "CI",
+  "CK",
+  "CL",
+  "CM",
+  "CN",
+  "CO",
+  "CP",
+  "CR",
+  "CS",
+  "CT",
+  "CU",
+  "CV",
+  "CW",
+  "CX",
+  "CY",
+  "DA",
+  "DB",
+  "DC",
+  "DD",
+  "DE",
+  "DF",
+  "DG",
+  "DH",
+  "DI",
+  "DJ",
+  "DK",
+  "DL",
+  "DM",
+  "DN",
+  "DO",
+  "DP",
+  "DR",
+  "DS",
+  "DT",
+  "DU",
+  "DV",
+  "DW",
+  "DX",
+  "DY",
+  "EA",
+  "EB",
+  "EC",
+  "ED",
+  "EE",
+  "EF",
+  "EG",
+  "EH",
+  "EI",
+  "EK",
+  "EL",
+  "EM",
+  "EN",
+  "EO",
+  "EP",
+  "EQ",
+  "ER",
+  "ES",
+  "ET",
+  "EU",
+  "EV",
+  "EW",
+  "EX",
+  "EZ",
+  "FA",
+  "FB",
+  "FC",
+  "FD",
+  "FE",
+  "FF",
+  "FG",
+  "FH",
+  "FI",
+  "FK",
+  "FL",
+  "FM",
+  "FN",
+  "FO",
+  "FP",
+  "FR",
+  "FS",
+  "FT",
+  "FU",
+  "FW",
+  "FX",
+  "FY",
+  "GA",
+  "GB",
+  "GC",
+  "GD",
+  "GE",
+  "GF",
+  "GG",
+  "GH",
+  "GI",
+  "GL",
+  "GM",
+  "GN",
+  "GO",
+  "GP",
+  "GR",
+  "GS",
+  "GT",
+  "GU",
+  "GV",
+  "GW",
+  "GX",
+  "GY",
+  "HA",
+  "HB",
+  "HC",
+  "HD",
+  "HE",
+  "HF",
+  "HG",
+  "HH",
+  "HI",
+  "HK",
+  "HL",
+  "HM",
+  "HN",
+  "HO",
+  "HP",
+  "HQ",
+  "HR",
+  "HS",
+  "HT",
+  "HU",
+  "HV",
+  "HW",
+  "HX",
+  "HY",
+  "HZ",
+  "IA",
+  "IB",
+  "IC",
+  "ID",
+  "IE",
+  "IF",
+  "IG",
+  "IH",
+  "II",
+  "IJ",
+  "IK",
+  "IL",
+  "IM",
+  "IN",
+  "IO",
+  "IP",
+  "IQ",
+  "IR",
+  "IS",
+  "IT",
+  "IU",
+  "IV",
+  "IW",
+  "IX",
+  "IZ",
+  "JA",
+  "JB",
+  "JC",
+  "JD",
+  "JE",
+  "JI",
+  "JJ",
+  "JK",
+  "JM",
+  "JO",
+  "JP",
+  "JR",
+  "JS",
+  "JT"
+ ],
+ "token_ids": [
+  32,
+  33,
+  34,
+  35,
+  36,
+  37,
+  38,
+  39,
+  40,
+  41,
+  42,
+  43,
+  44,
+  45,
+  46,
+  47,
+  48,
+  49,
+  50,
+  51,
+  52,
+  53,
+  54,
+  55,
+  56,
+  57,
+  5840,
+  1803,
+  1646,
+  1745,
+  13276,
+  8018,
+  1825,
+  28946,
+  15015,
+  29595,
+  11568,
+  939,
+  1354,
+  1058,
+  18183,
+  2456,
+  88898,
+  905,
+  1846,
+  802,
+  33869,
+  7839,
+  14006,
+  2860,
+  2926,
+  22828,
+  6844,
+  9798,
+  4738,
+  9265,
+  11261,
+  19278,
+  36513,
+  93801,
+  8335,
+  14544,
+  85266,
+  9110,
+  28000,
+  15137,
+  4525,
+  25261,
+  12717,
+  7116,
+  17078,
+  14497,
+  57339,
+  74909,
+  52072,
+  19305,
+  4887,
+  12607,
+  3580,
+  6281,
+  2036,
+  9362,
+  8533,
+  2080,
+  10911,
+  2925,
+  3040,
+  9690,
+  27731,
+  8023,
+  6901,
+  8702,
+  6211,
+  1123,
+  16307,
+  18990,
+  64045,
+  63037,
+  33380,
+  6151,
+  3392,
+  5449,
+  3967,
+  1113,
+  5095,
+  51923,
+  49600,
+  17099,
+  51483,
+  17756,
+  16037,
+  8135,
+  30237,
+  5683,
+  9992,
+  7444,
+  5751,
+  10284,
+  20887,
+  59884,
+  52396,
+  16103,
+  67547,
+  18535,
+  8006,
+  7263,
+  1425,
+  6878,
+  14453,
+  9097,
+  44072,
+  76089,
+  68720,
+  2662,
+  2629,
+  923,
+  6548,
+  8924,
+  52194,
+  622,
+  1515,
+  1300,
+  37523,
+  44473,
+  36530,
+  3152,
+  93924,
+  3505,
+  15731,
+  6542,
+  14176,
+  11091,
+  1686,
+  11660,
+  80440,
+  18836,
+  26132,
+  5934,
+  24794,
+  40229,
+  3660,
+  11361,
+  10191,
+  8225,
+  3860,
+  78413,
+  17680,
+  15900,
+  78138,
+  15653,
+  5213,
+  22150,
+  39500,
+  10460,
+  35131,
+  21563,
+  43194,
+  27127,
+  3697,
+  20011,
+  24368,
+  15058,
+  23658,
+  8362,
+  16035,
+  24583,
+  52857,
+  38403,
+  60456,
+  81519,
+  40097,
+  16522,
+  29722,
+  21756,
+  18567,
+  1736,
+  48043,
+  87013,
+  22456,
+  23165,
+  55523,
+  13097,
+  50397,
+  41741,
+  23073,
+  6401,
+  86538,
+  16585,
+  11622,
+  2464,
+  84982,
+  75516,
+  36984,
+  58795,
+  47217,
+  59675,
+  5681,
+  3151,
+  1271,
+  887,
+  5203,
+  2685,
+  1849,
+  72470,
+  5370,
+  74063,
+  27629,
+  1655,
+  1728,
+  669,
+  3682,
+  3191,
+  59865,
+  2712,
+  1580,
+  922,
+  77243,
+  2990,
+  78493,
+  5228,
+  2750,
+  42711,
+  44568,
+  56402,
+  48236,
+  38993,
+  43559,
+  61250,
+  32942,
+  86302,
+  25310,
+  26313,
+  81770,
+  12185,
+  78382
+ ],
+ "attention": "bidirectional",
+ "base_model": "Qwen/Qwen3.5-9B",
+ "marker": "<|fim_suffix|>",
+ "temperatures": {
+  "choice": 1.0,
+  "noul": 1.0,
+  "score": 1.0
+ },
+ "max_pixels": 1638400,
+ "readout_dtype": "float32",
+ "backbone": null,
+ "format_version": 1
+}

licenses/Qwen3.5-LICENSE

@@ -0,0 +1,202 @@
+
+                                 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 2026 Alibaba Cloud
+
+   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.

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d9658310bbe9af08d45755f3918156cb08eb02bda775423a50d5e810477be3
+size 5348479776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bdf23049ff83354064bea7d7726e7f6e3c4b05fbe277340e84454e00f46920
+size 5290354536

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f23118b4cdd0b23f48caf1a87428cb2a9b8971a229be426f38d793aee84ec18
+size 5323992232

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737cf8aa9aaa60818988e26067da6e073b07d4be98ef5556d99599af9c50e301
+size 822652448

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 16785390048}, "weight_map": {"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors", "visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors", "visual.pos_embed.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "visual.merger.norm.weight": "model-00001-of-00004.safetensors", "visual.merger.norm.bias": "model-00001-of-00004.safetensors", "visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors", "visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors", "visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors", "visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors", "language_model.embed_tokens.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.A_log": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.A_log": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.A_log": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.A_log": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.A_log": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.dt_bias": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.A_log": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.conv1d.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.norm.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.out_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.in_proj_z.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.in_proj_b.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.linear_attn.in_proj_a.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.in_proj_z.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.in_proj_b.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.linear_attn.in_proj_a.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.dt_bias": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.A_log": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.conv1d.weight": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.norm.weight": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.out_proj.weight": "model-00003-of-00004.safetensors", "language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors", "language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", "language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "language_model.norm.weight": "model-00004-of-00004.safetensors"}}

processor_config.json

@@ -0,0 +1,61 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 1638400,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "max_video_tokens": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

readout.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94676a77dde652423169fe319bfafb29ec1a0615ec8369554ee89da4cf520823
+size 4178000

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5cd9732badce41de57e6efce8302930ded1c1188c5f81feb2bd6c24c4a1941f
+size 19989339

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": false,
+  "merges_file": null,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen3_5Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}