初始化项目，由ModelHub XC社区提供模型

Model: loaiabdalslam/SLM-FRIDGE-ICED-0.5B-32BQWEN Source: Original Platform
2026-07-03 10:30:18 +08:00
commit 5a07c9e7ff
13 changed files with 152119 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,290 @@
+---
+language:
+- en
+
+license: apache-2.0
+
+library_name: transformers
+
+pipeline_tag: text-generation
+
+tags:
+- small-language-model
+- causal-lm
+- qwen2
+- 0.5b
+- reasoning
+- benchmarked
+
+base_model: Qwen/Qwen2.5-32B
+
+model-index:
+- name: SLM-FRIDGE-0.5B
+  results:
+
+  - task:
+      type: multiple-choice
+      name: Massive Multitask Language Understanding (MMLU)
+    dataset:
+      name: MMLU
+      type: cais/mmlu
+    metrics:
+    - type: accuracy
+      value: 47.59
+      name: Accuracy
+
+  - task:
+      type: question-answering
+      name: ARC Challenge
+    dataset:
+      name: ARC Challenge
+      type: ai2_arc
+      config: ARC-Challenge
+    metrics:
+    - type: accuracy
+      value: 29.01
+      name: Accuracy
+
+    - type: normalized_accuracy
+      value: 32.76
+      name: Normalized Accuracy
+
+  - task:
+      type: mathematical-reasoning
+      name: GSM8K
+    dataset:
+      name: GSM8K
+      type: gsm8k
+    metrics:
+    - type: exact_match
+      value: 35.33
+      name: Exact Match (5-shot)
+
+  - task:
+      type: commonsense-reasoning
+      name: HellaSwag
+    dataset:
+      name: HellaSwag
+      type: hellaswag
+    metrics:
+    - type: accuracy
+      value: 40.68
+      name: Accuracy
+
+    - type: normalized_accuracy
+      value: 52.18
+      name: Normalized Accuracy
+
+  - task:
+      type: multiple-choice
+      name: TruthfulQA MC2
+    dataset:
+      name: TruthfulQA
+      type: truthful_qa
+      config: multiple_choice
+    metrics:
+    - type: accuracy
+      value: 39.77
+      name: Accuracy
+
+  - task:
+      type: commonsense-reasoning
+      name: Winogrande
+    dataset:
+      name: Winogrande
+      type: winogrande
+    metrics:
+    - type: accuracy
+      value: 56.51
+      name: Accuracy
+---
+# SLM FRIDGE - ICED MODEL [32b Qwen Shadow-v1.5.p] (Quantum-Inspired Cross-Dimensional Shadow Projection)
+
+Welcome to the **SLM FRIDGE - ICED MODEL** repository. This project features a revolutionary Cross-Dimensional Manifold Projection (CDMP) engine that takes high-dimensional alignment properties from 7B models and projects them directly into 1.5B (1B-class) student models without traditional student-teacher training or memory-intensive distillation.
+
+![730749823_1552302703228403_6044455848375536848_n](https://cdn-uploads.huggingface.co/production/uploads/64c4620f3e80e593568f3875/mtwdeRbaN_Z3g9ATHsLoG.jpeg)
+
+---
+
+## Mathematical Philosophy: Cross-Dimensional Manifold Projection (CDMP)
+
+
+Traditional parameter merging assumes identical parameter dimensions between models.  
+CDMP transfers instruction-following behavior from a higher-dimensional teacher model into a lower-dimensional student model through manifold projection.
+
+## 1. Extracting the Instruction Alignment Delta
+
+The instruction-tuning signal is isolated from the teacher model:
+
+$$
+\Delta W_{\text{high}}
+=
+W_{\text{teacher\_instruct}}
+-
+W_{\text{teacher\_base}}
+$$
+
+---
+
+## 2. Manifold Subspace Decomposition
+
+The alignment delta is decomposed using Singular Value Decomposition (SVD):
+
+$$
+\Delta W_{\text{high}}
+\approx
+U_{\text{high}}
+\Sigma_{\text{high}}
+V_{\text{high}}^{T}
+$$
+
+Where:
+
+$$
+U_{\text{high}} \in \mathbb{R}^{m \times r}
+$$
+
+$$
+\Sigma_{\text{high}} \in \mathbb{R}^{r \times r}
+$$
+
+$$
+V_{\text{high}} \in \mathbb{R}^{n \times r}
+$$
+
+---
+
+## 3. Cross-Dimensional Projection
+
+The singular manifolds are projected into the student's dimensional space while preserving the dominant singular energy spectrum.
+
+Output-space projection:
+
+$$
+U_{\text{low}}
+=
+\operatorname{Project}
+\left(
+U_{\text{high}},
+d_{\text{low,out}}
+\right)
+$$
+
+Input-space projection:
+
+$$
+V_{\text{low}}
+=
+\operatorname{Project}
+\left(
+V_{\text{high}},
+d_{\text{low,in}}
+\right)
+$$
+
+Projected alignment manifold:
+
+$$
+\Delta W_{\text{proj}}
+=
+U_{\text{low}}
+\Sigma_{\text{high}}
+V_{\text{low}}^{T}
+$$
+
+---
+
+## 4. Instruction Manifold Infusion
+
+The projected manifold is infused into the student base model:
+
+$$
+W_{\text{ICED}}
+=
+W_{\text{student\_base}}
+
+\alpha
+\Delta W_{\text{proj}}
+$$
+
+Expanded form:
+
+$$
+W_{\text{ICED}}
+=
+W_{\text{student\_base}}
+
+\alpha
+\left(
+U_{\text{low}}
+\Sigma_{\text{high}}
+V_{\text{low}}^{T}
+\right)
+$$
+
+Where:
+
+- **α** = infusion coefficient
+- **α = 0** preserves the original student model
+- Higher **α** values increase transferred instruction behavior
+
+---
+
+## Conceptual Overview
+
+CDMP treats instruction tuning as a transferable low-rank manifold rather than a direct parameter delta.
+
+The procedure is:
+
+1. Extract the instruction alignment delta from the teacher.
+2. Decompose the delta into its dominant singular structures.
+3. Project those structures into the student's dimensional space.
+4. Reconstruct the projected manifold.
+5. Infuse the resulting manifold into the student model.
+
+### Transfer Path
+
+$$
+\text{Teacher}_{7B}
+\;\longrightarrow\;
+\text{CDMP Projection}
+\;\longrightarrow\;
+\text{Student}_{1.5B}
+$$
+
+This enables cross-scale instruction transfer without requiring identical parameter dimensions.
+---
+
+## Technical Performance Benchmark & Comprehensive Comparison
+
+Below is the comparative report highlighting the performance profile of the original models alongside our newly minted **Cross-Projected ICED Model** (rank = 24):
+
+
+---
+
+### 1. Output Generational Preview
+
+#### **Test Prompt:**
+> *"Machine learning is transforming the world by"*
+
+#### **Original Base Student (7B) Generation:**
+> Machine learning is transforming the world by providing powerful tools for solving complex problems in a wide range of domains. In this post, we’ll explore how machine learning can be used to solve real-world problems and make predictions about future events.
+In order to do that, let’s first look at what exactly machine learning is. Machine Learning (ML
+
+#### **ICED Model Generation (With 32B Infused Brain):**
+> Machine learning is transforming the world by providing powerful insights into complex data. But what about privacy? Can we use machine learning to protect our personal information while still getting valuable results?
+The answer lies in differential privacy, a mathematical framework that ensures sensitive data remains private even as it’s used for analysis.
+In this blog post, we’ll explore
+
+---
+
+##  Production Deployment Instructions
+
+The resulting model weights and tokenizer are completely ready for production:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("loaiabdalslam/SLM-FRIDGE-ICED-0.5B-32BQWEN")
+model = AutoModelForCausalLM.from_pretrained("loaiabdalslam/SLM-FRIDGE-ICED-0.5B-32BQWEN")
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.56.0"
+}
--- a/iced_model_production.log
+++ b/iced_model_production.log
@@ -0,0 +1,21 @@
+2026-06-24 08:20:32,690 [INFO] Target compute device selected: cpu
+2026-06-24 08:20:32,696 [INFO] ======================================
+2026-06-24 08:20:32,697 [INFO] Profiling and evaluating Original Base Student Model (1.5B)...
+2026-06-24 08:20:32,698 [INFO] ======================================
+2026-06-24 08:20:54,647 [INFO] ======================================
+2026-06-24 08:20:54,648 [INFO] Synthesizing the hybrid CDMP ICED Model...
+2026-06-24 08:20:54,649 [INFO] ======================================
+2026-06-24 08:20:54,650 [INFO] === STEP 1: Loading student tokenizer ===
+2026-06-24 08:20:54,898 [INFO] === STEP 2: Loading student base model as structural target ===
+2026-06-24 08:20:57,325 [INFO] Detected 24 layers in Student Model (Qwen/Qwen2.5-0.5B)
+2026-06-24 08:20:57,524 [INFO] === STEP 3: Loading Teacher Base Model and filtering active keys to conserve RAM ===
+2026-06-24 08:27:53,269 [INFO] Detected 64 layers in Teacher Base Model (Qwen/Qwen2.5-32B)
+2026-06-24 08:28:21,610 [INFO] === STEP 4: Loading Teacher Instruct Model and progressively filtering layers ===
+2026-06-24 08:35:44,038 [INFO] === STEP 5: Progressively decomposing and projecting 7B shadows down to 1.5B dimensions ===
+2026-06-24 08:40:00,194 [INFO] === STEP 6: Injecting projected 7B shadow into 1.5B student manifold ===
+2026-06-24 08:40:01,322 [INFO] Assembling and instantiating final QISI student assets...
+2026-06-24 08:40:03,722 [INFO] Successfully merged and projected 7B Instruct alignments into 1.5B Base Student!
+2026-06-24 08:40:03,728 [INFO] Profiling and evaluating synthesized CDMP ICED Model...
+2026-06-24 08:40:15,575 [INFO] Production-ready causal weights successfully saved to: ./slm_fridge_iced_model_production
+2026-06-24 08:40:15,582 [INFO] Successfully generated comparison report and exported to: ./slm_fridge_iced_model_production/README.md
+2026-06-24 08:40:15,588 [INFO] Uploading model assets to Hugging Face Hub Registry: loaiabdalslam/SLM-FRIDGE-ICED-0.5B-32BQWEN-Shdow
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85eaa14ab5ce18a96fcb27c2c365a50d6e713e2710870b78c17ca6d812f44d9b
+size 988097536
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/vocab.json
+++ b/vocab.json