Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-471/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+model_name: typescript-slm-7b
+tags:
+- typescript
+- code-generation
+- react
+- nextjs
+- angular
+- nodejs
+- lora
+- sft
+- 7b
+
+- transformers
+- trl
+license: mit
+pipeline_tag: text-generation
+language:
+- en
+---
+
+# TypeScript SLM 7B
+
+Standard 7B TypeScript model for TypeScript code generation, optimized for React, Next.js, Angular, and Node.js.
+
+## Model Details
+
+- **Base Model**: [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
+- **Model Size**: 7B parameters
+- **Training Method**: LoRA (Low-Rank Adaptation)
+- **Context Length**: 2048 tokens
+- **LoRA Rank**: 64
+- **Training Dataset**: 5,000 high-quality TypeScript samples
+
+
+
+
+## Training Configuration
+
+- Batch Size: 2
+- Gradient Accumulation: 16
+- Effective Batch Size: 32
+- Learning Rate: 0.0001
+- Epochs: 3
+- Hardware: Google Colab A100 40GB
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base_model = "Qwen/Qwen2.5-Coder-7B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(
+    base_model,
+    device_map="auto",
+    torch_dtype="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(model, "sylvester-francis/typescript-slm-7b")
+
+# Generate code
+prompt = "Write a React component with TypeScript:"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Repository
+
+https://github.com/sylvester-francis/slm-typescript-model

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab56d83ad19a7f2e6388846b3171f9b2458c079dee2cb696e94de55b93cd53e
+size 645975704

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
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

checkpoint-471/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-471/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-471/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab56d83ad19a7f2e6388846b3171f9b2458c079dee2cb696e94de55b93cd53e
+size 645975704

checkpoint-471/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
+}

checkpoint-471/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 %}

checkpoint-471/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a73ed61802bc8fc9c320cc8f018b4cc4980d7d5836fea294c147d7143f9bd3
+size 1292176635

checkpoint-471/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c8639649333e7a2e28bfad591aeb10b8535c048e234137c7b457e9fb11e659
+size 14645

checkpoint-471/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43ec84ce17ac70535435458670af11900888cd9a53a55de5cc4f7045427326a
+size 1383

checkpoint-471/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440e88cdd2b8f02a69e37eb0571770eaefbce9ec77b189187cfdbff43e7aac63
+size 1465

checkpoint-471/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-471/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-471/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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-471/trainer_state.json

@@ -0,0 +1,504 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.6209051959216595,
+      "epoch": 0.064,
+      "grad_norm": 0.148471400141716,
+      "learning_rate": 6e-05,
+      "loss": 0.8015,
+      "mean_token_accuracy": 0.8045522212982178,
+      "num_tokens": 322872.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7808685328811407,
+      "epoch": 0.128,
+      "grad_norm": 0.14745265245437622,
+      "learning_rate": 9.998101535124758e-05,
+      "loss": 0.7506,
+      "mean_token_accuracy": 0.8135283548384905,
+      "num_tokens": 544608.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.717990642413497,
+      "epoch": 0.192,
+      "grad_norm": 0.2732456922531128,
+      "learning_rate": 9.976760358471686e-05,
+      "loss": 0.7465,
+      "mean_token_accuracy": 0.8131686106324196,
+      "num_tokens": 671386.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7955288266763091,
+      "epoch": 0.256,
+      "grad_norm": 0.19003289937973022,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.7744,
+      "mean_token_accuracy": 0.8094954665750265,
+      "num_tokens": 750980.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7189005561172962,
+      "epoch": 0.32,
+      "grad_norm": 0.1355617344379425,
+      "learning_rate": 9.86345329809282e-05,
+      "loss": 0.7272,
+      "mean_token_accuracy": 0.8176465440541506,
+      "num_tokens": 1071850.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.6766207502223551,
+      "epoch": 0.384,
+      "grad_norm": 0.1723758429288864,
+      "learning_rate": 9.772025009397537e-05,
+      "loss": 0.6811,
+      "mean_token_accuracy": 0.828043271228671,
+      "num_tokens": 1291954.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.7161493487656116,
+      "epoch": 0.448,
+      "grad_norm": 0.2560935318470001,
+      "learning_rate": 9.657955440256395e-05,
+      "loss": 0.7082,
+      "mean_token_accuracy": 0.8225393697619439,
+      "num_tokens": 1419346.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.7365618254989386,
+      "epoch": 0.512,
+      "grad_norm": 0.17795203626155853,
+      "learning_rate": 9.521785803487889e-05,
+      "loss": 0.7271,
+      "mean_token_accuracy": 0.8189035877585411,
+      "num_tokens": 1526718.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.7039074258878827,
+      "epoch": 0.576,
+      "grad_norm": 0.14803574979305267,
+      "learning_rate": 9.364162167569907e-05,
+      "loss": 0.713,
+      "mean_token_accuracy": 0.8223464518785477,
+      "num_tokens": 1845437.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.6674862142652274,
+      "epoch": 0.64,
+      "grad_norm": 0.18329669535160065,
+      "learning_rate": 9.185832391312644e-05,
+      "loss": 0.6691,
+      "mean_token_accuracy": 0.8296808384358882,
+      "num_tokens": 2056702.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.6854978334158659,
+      "epoch": 0.704,
+      "grad_norm": 0.303744375705719,
+      "learning_rate": 8.987642575578545e-05,
+      "loss": 0.6792,
+      "mean_token_accuracy": 0.8301461268216371,
+      "num_tokens": 2175930.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.723753459751606,
+      "epoch": 0.768,
+      "grad_norm": 0.15608754754066467,
+      "learning_rate": 8.770533048884482e-05,
+      "loss": 0.7203,
+      "mean_token_accuracy": 0.8180315487086773,
+      "num_tokens": 2309721.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.7012022797018289,
+      "epoch": 0.832,
+      "grad_norm": 0.15858694911003113,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.696,
+      "mean_token_accuracy": 0.8232303861528635,
+      "num_tokens": 2611586.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6653847711160779,
+      "epoch": 0.896,
+      "grad_norm": 0.19071699678897858,
+      "learning_rate": 8.283760120238672e-05,
+      "loss": 0.671,
+      "mean_token_accuracy": 0.8293524540960788,
+      "num_tokens": 2799782.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.6853383446112276,
+      "epoch": 0.96,
+      "grad_norm": 0.31338417530059814,
+      "learning_rate": 8.016406254043595e-05,
+      "loss": 0.6867,
+      "mean_token_accuracy": 0.8288525927811861,
+      "num_tokens": 2900442.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7035530685774378,
+      "epoch": 1.0192,
+      "grad_norm": 0.16408444941043854,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.8308813571929932,
+      "num_tokens": 3028578.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.638525976985693,
+      "epoch": 1.0832,
+      "grad_norm": 0.17635616660118103,
+      "learning_rate": 7.440100115804991e-05,
+      "loss": 0.6378,
+      "mean_token_accuracy": 0.8364114947617054,
+      "num_tokens": 3336335.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.6012187819927931,
+      "epoch": 1.1472,
+      "grad_norm": 0.2054251879453659,
+      "learning_rate": 7.133882177482019e-05,
+      "loss": 0.5823,
+      "mean_token_accuracy": 0.848956223204732,
+      "num_tokens": 3532330.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5475345650687814,
+      "epoch": 1.2112,
+      "grad_norm": 0.35844680666923523,
+      "learning_rate": 6.817539852819149e-05,
+      "loss": 0.529,
+      "mean_token_accuracy": 0.8619996141642332,
+      "num_tokens": 3643232.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5675112227909267,
+      "epoch": 1.2752,
+      "grad_norm": 0.2158765196800232,
+      "learning_rate": 6.492574055008473e-05,
+      "loss": 0.5719,
+      "mean_token_accuracy": 0.8530487548559904,
+      "num_tokens": 3801015.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.6614907115697861,
+      "epoch": 1.3392,
+      "grad_norm": 0.18693146109580994,
+      "learning_rate": 6.16052661204734e-05,
+      "loss": 0.6457,
+      "mean_token_accuracy": 0.8346318401396274,
+      "num_tokens": 4099106.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5810376997105777,
+      "epoch": 1.4032,
+      "grad_norm": 0.26153114438056946,
+      "learning_rate": 5.8229729514036705e-05,
+      "loss": 0.5615,
+      "mean_token_accuracy": 0.8529797650873661,
+      "num_tokens": 4282361.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5295255590695888,
+      "epoch": 1.4672,
+      "grad_norm": 0.3696475028991699,
+      "learning_rate": 5.481514625265709e-05,
+      "loss": 0.5098,
+      "mean_token_accuracy": 0.8662762496620416,
+      "num_tokens": 4379994.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.5454086041543633,
+      "epoch": 1.5312000000000001,
+      "grad_norm": 0.2196943759918213,
+      "learning_rate": 5.1377717118408105e-05,
+      "loss": 0.5529,
+      "mean_token_accuracy": 0.8564440425485372,
+      "num_tokens": 4563598.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.5975794316269457,
+      "epoch": 1.5952,
+      "grad_norm": 0.1890081763267517,
+      "learning_rate": 4.7933751287559335e-05,
+      "loss": 0.5917,
+      "mean_token_accuracy": 0.8455708675086498,
+      "num_tokens": 4856273.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.5899994445033372,
+      "epoch": 1.6592,
+      "grad_norm": 0.26096731424331665,
+      "learning_rate": 4.449958895029604e-05,
+      "loss": 0.559,
+      "mean_token_accuracy": 0.8543823335319758,
+      "num_tokens": 5032916.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.49704947993159293,
+      "epoch": 1.7231999999999998,
+      "grad_norm": 0.44323092699050903,
+      "learning_rate": 4.109152378329036e-05,
+      "loss": 0.4836,
+      "mean_token_accuracy": 0.8725535746663808,
+      "num_tokens": 5124767.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.5848865715786815,
+      "epoch": 1.7872,
+      "grad_norm": 0.2207033932209015,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.5967,
+      "mean_token_accuracy": 0.8442678898572922,
+      "num_tokens": 5335786.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.5775562720373273,
+      "epoch": 1.8512,
+      "grad_norm": 0.22754396498203278,
+      "learning_rate": 3.4418163846202944e-05,
+      "loss": 0.5806,
+      "mean_token_accuracy": 0.8495132122188807,
+      "num_tokens": 5610648.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.5726861954666674,
+      "epoch": 1.9152,
+      "grad_norm": 0.3043781816959381,
+      "learning_rate": 3.118453140260823e-05,
+      "loss": 0.5348,
+      "mean_token_accuracy": 0.8609532874077559,
+      "num_tokens": 5771094.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.5179639799054712,
+      "epoch": 1.9792,
+      "grad_norm": 0.4674849808216095,
+      "learning_rate": 2.804017055763149e-05,
+      "loss": 0.4871,
+      "mean_token_accuracy": 0.873416931182146,
+      "num_tokens": 5849068.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.5768430942820536,
+      "epoch": 2.0384,
+      "grad_norm": 0.18999820947647095,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5572,
+      "mean_token_accuracy": 0.8515819480290284,
+      "num_tokens": 6057156.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.5366130633279681,
+      "epoch": 2.1024,
+      "grad_norm": 0.24353531002998352,
+      "learning_rate": 2.207844407871929e-05,
+      "loss": 0.5415,
+      "mean_token_accuracy": 0.8581785768270492,
+      "num_tokens": 6338527.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.5128508457448333,
+      "epoch": 2.1664,
+      "grad_norm": 0.31620872020721436,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.4713,
+      "mean_token_accuracy": 0.874517310038209,
+      "num_tokens": 6502869.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.45380836687982085,
+      "epoch": 2.2304,
+      "grad_norm": 0.498538613319397,
+      "learning_rate": 1.6645993887429345e-05,
+      "loss": 0.3897,
+      "mean_token_accuracy": 0.8966626085340976,
+      "num_tokens": 6584851.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5007886356674135,
+      "epoch": 2.2944,
+      "grad_norm": 0.27758654952049255,
+      "learning_rate": 1.4160874341577446e-05,
+      "loss": 0.512,
+      "mean_token_accuracy": 0.8663116212934255,
+      "num_tokens": 6823494.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.5115637780167163,
+      "epoch": 2.3584,
+      "grad_norm": 0.2892008423805237,
+      "learning_rate": 1.1845796590009683e-05,
+      "loss": 0.5388,
+      "mean_token_accuracy": 0.8598299425095319,
+      "num_tokens": 7094827.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.5195480000693351,
+      "epoch": 2.4224,
+      "grad_norm": 0.32241010665893555,
+      "learning_rate": 9.711744716951093e-06,
+      "loss": 0.4785,
+      "mean_token_accuracy": 0.8739933516830206,
+      "num_tokens": 7254184.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.43473423006944356,
+      "epoch": 2.4864,
+      "grad_norm": 0.5118304491043091,
+      "learning_rate": 7.768843913876756e-06,
+      "loss": 0.3564,
+      "mean_token_accuracy": 0.9055155254900455,
+      "num_tokens": 7328662.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.5615584854967892,
+      "epoch": 2.5504,
+      "grad_norm": 0.22603784501552582,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.5467,
+      "mean_token_accuracy": 0.8580426320433616,
+      "num_tokens": 7596240.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.5025078831706196,
+      "epoch": 2.6144,
+      "grad_norm": 0.28563639521598816,
+      "learning_rate": 4.492417883833155e-06,
+      "loss": 0.5228,
+      "mean_token_accuracy": 0.8626903854310513,
+      "num_tokens": 7851845.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.4571648451499641,
+      "epoch": 2.6784,
+      "grad_norm": 0.36225077509880066,
+      "learning_rate": 3.1744379401472677e-06,
+      "loss": 0.4437,
+      "mean_token_accuracy": 0.8820992216467858,
+      "num_tokens": 8000771.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.3912047180114314,
+      "epoch": 2.7424,
+      "grad_norm": 0.7312374711036682,
+      "learning_rate": 2.0786258770873647e-06,
+      "loss": 0.3383,
+      "mean_token_accuracy": 0.9096384748816491,
+      "num_tokens": 8066913.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.572740061301738,
+      "epoch": 2.8064,
+      "grad_norm": 0.2328728884458542,
+      "learning_rate": 1.210180868628219e-06,
+      "loss": 0.5658,
+      "mean_token_accuracy": 0.8527029093354941,
+      "num_tokens": 8361279.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.4809988150373101,
+      "epoch": 2.8704,
+      "grad_norm": 0.2871045470237732,
+      "learning_rate": 5.732233263245845e-07,
+      "loss": 0.4829,
+      "mean_token_accuracy": 0.8712109945714474,
+      "num_tokens": 8591369.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.44853435261175034,
+      "epoch": 2.9344,
+      "grad_norm": 0.36524489521980286,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.4225,
+      "mean_token_accuracy": 0.8876127731055021,
+      "num_tokens": 8727528.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.4016893004532903,
+      "epoch": 2.9984,
+      "grad_norm": 0.7618845701217651,
+      "learning_rate": 4.746387470044855e-09,
+      "loss": 0.3347,
+      "mean_token_accuracy": 0.9090729501098395,
+      "num_tokens": 8787031.0,
+      "step": 470
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 471,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.817612303232717e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-471/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501bdc82eec738806ab8453a49fe8f3e08523456362c94171930835d328452db
+size 6161

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}