Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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-229/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-687/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B
+- lora
+- transformers
+---
+
+# 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 0.18.1

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",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_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:cd9d71e04cf282afc819b9f4ff75c323131ca4aa8d7a450fa38993ded4b41a8d
+size 161533192

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-229/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-229/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",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-229/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9d71e04cf282afc819b9f4ff75c323131ca4aa8d7a450fa38993ded4b41a8d
+size 161533192

checkpoint-229/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-229/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-229/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03a623f8d1bf04250f49ed77dd2b43687f58e88752e82d23f55669614289488
+size 323296891

checkpoint-229/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ce8d191fa9c96a85bae3594cdf5d4c5015782b0d7729a0d842941377b2931b
+size 14645

checkpoint-229/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9849290a22737a7e0c145d0f0c19bd3b38ea5d3bf1c67216a5662a4c68606bf3
+size 1465

checkpoint-229/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
+  }
+}

checkpoint-229/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
+size 11421995

checkpoint-229/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-229/trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_global_step": 229,
+  "best_metric": 0.22333618998527527,
+  "best_model_checkpoint": "./lora_qwen7b_python_abdiff_v1/checkpoint-229",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 229,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043835616438356165,
+      "grad_norm": 0.210234135389328,
+      "learning_rate": 3.913043478260869e-06,
+      "loss": 0.6169,
+      "step": 10
+    },
+    {
+      "epoch": 0.08767123287671233,
+      "grad_norm": 0.25168153643608093,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.6133,
+      "step": 20
+    },
+    {
+      "epoch": 0.13150684931506848,
+      "grad_norm": 0.19567625224590302,
+      "learning_rate": 1.2608695652173912e-05,
+      "loss": 0.5688,
+      "step": 30
+    },
+    {
+      "epoch": 0.17534246575342466,
+      "grad_norm": 0.30335545539855957,
+      "learning_rate": 1.6956521739130433e-05,
+      "loss": 0.5225,
+      "step": 40
+    },
+    {
+      "epoch": 0.2191780821917808,
+      "grad_norm": 0.24670398235321045,
+      "learning_rate": 2.1304347826086958e-05,
+      "loss": 0.3971,
+      "step": 50
+    },
+    {
+      "epoch": 0.26301369863013696,
+      "grad_norm": 0.12593719363212585,
+      "learning_rate": 2.565217391304348e-05,
+      "loss": 0.2952,
+      "step": 60
+    },
+    {
+      "epoch": 0.30684931506849317,
+      "grad_norm": 0.11282460391521454,
+      "learning_rate": 3e-05,
+      "loss": 0.2592,
+      "step": 70
+    },
+    {
+      "epoch": 0.3506849315068493,
+      "grad_norm": 0.10163664072751999,
+      "learning_rate": 2.9514563106796115e-05,
+      "loss": 0.2402,
+      "step": 80
+    },
+    {
+      "epoch": 0.39452054794520547,
+      "grad_norm": 0.09871397167444229,
+      "learning_rate": 2.9029126213592237e-05,
+      "loss": 0.2251,
+      "step": 90
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 0.09532774984836578,
+      "learning_rate": 2.854368932038835e-05,
+      "loss": 0.2132,
+      "step": 100
+    },
+    {
+      "epoch": 0.4821917808219178,
+      "grad_norm": 0.08755984157323837,
+      "learning_rate": 2.8058252427184466e-05,
+      "loss": 0.2086,
+      "step": 110
+    },
+    {
+      "epoch": 0.5260273972602739,
+      "grad_norm": 0.09590521454811096,
+      "learning_rate": 2.757281553398058e-05,
+      "loss": 0.198,
+      "step": 120
+    },
+    {
+      "epoch": 0.5698630136986301,
+      "grad_norm": 0.09363297373056412,
+      "learning_rate": 2.7087378640776702e-05,
+      "loss": 0.1954,
+      "step": 130
+    },
+    {
+      "epoch": 0.6136986301369863,
+      "grad_norm": 0.09872984886169434,
+      "learning_rate": 2.6601941747572816e-05,
+      "loss": 0.1902,
+      "step": 140
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 0.12371695041656494,
+      "learning_rate": 2.611650485436893e-05,
+      "loss": 0.1892,
+      "step": 150
+    },
+    {
+      "epoch": 0.7013698630136986,
+      "grad_norm": 0.10814935714006424,
+      "learning_rate": 2.563106796116505e-05,
+      "loss": 0.1808,
+      "step": 160
+    },
+    {
+      "epoch": 0.7452054794520548,
+      "grad_norm": 0.12739220261573792,
+      "learning_rate": 2.5145631067961167e-05,
+      "loss": 0.1815,
+      "step": 170
+    },
+    {
+      "epoch": 0.7890410958904109,
+      "grad_norm": 0.1482655555009842,
+      "learning_rate": 2.466019417475728e-05,
+      "loss": 0.1652,
+      "step": 180
+    },
+    {
+      "epoch": 0.8328767123287671,
+      "grad_norm": 0.13323327898979187,
+      "learning_rate": 2.41747572815534e-05,
+      "loss": 0.1663,
+      "step": 190
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.1497439742088318,
+      "learning_rate": 2.3689320388349514e-05,
+      "loss": 0.1693,
+      "step": 200
+    },
+    {
+      "epoch": 0.9205479452054794,
+      "grad_norm": 0.16727504134178162,
+      "learning_rate": 2.3203883495145632e-05,
+      "loss": 0.1588,
+      "step": 210
+    },
+    {
+      "epoch": 0.9643835616438357,
+      "grad_norm": 0.159692645072937,
+      "learning_rate": 2.2718446601941746e-05,
+      "loss": 0.1489,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.22333618998527527,
+      "eval_runtime": 65.6094,
+      "eval_samples_per_second": 18.808,
+      "eval_steps_per_second": 9.404,
+      "step": 229
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 687,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.450291044029481e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-229/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee7536bf82641b420fe5dff159b13045ace05d8fdb821d389fc6c8d3f91b668
+size 5841

checkpoint-687/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B
+- lora
+- transformers
+---
+
+# 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 0.18.1

checkpoint-687/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",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-687/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c334a1f83fa8f859f33e1f14ebaab7f7b2150e59617b86cf3289908ce6437c7d
+size 161533192

checkpoint-687/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-687/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-687/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7126a10c37739b45fcdc7ab922cd1669528d2fa24eb27e4c44bbda93cb9531b
+size 323296891

checkpoint-687/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495a62da85717f635c90949f313752f9dd80d1abbe200d99f2f2e32f8c13571c
+size 14645

checkpoint-687/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d8863f6c759aeecdd8b20260ce8108c49a869c21a993c7a3a90e4a9a9559c6
+size 1465

checkpoint-687/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
+  }
+}

checkpoint-687/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
+size 11421995

checkpoint-687/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-687/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": 229,
+  "best_metric": 0.22333618998527527,
+  "best_model_checkpoint": "./lora_qwen7b_python_abdiff_v1/checkpoint-229",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 687,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043835616438356165,
+      "grad_norm": 0.210234135389328,
+      "learning_rate": 3.913043478260869e-06,
+      "loss": 0.6169,
+      "step": 10
+    },
+    {
+      "epoch": 0.08767123287671233,
+      "grad_norm": 0.25168153643608093,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.6133,
+      "step": 20
+    },
+    {
+      "epoch": 0.13150684931506848,
+      "grad_norm": 0.19567625224590302,
+      "learning_rate": 1.2608695652173912e-05,
+      "loss": 0.5688,
+      "step": 30
+    },
+    {
+      "epoch": 0.17534246575342466,
+      "grad_norm": 0.30335545539855957,
+      "learning_rate": 1.6956521739130433e-05,
+      "loss": 0.5225,
+      "step": 40
+    },
+    {
+      "epoch": 0.2191780821917808,
+      "grad_norm": 0.24670398235321045,
+      "learning_rate": 2.1304347826086958e-05,
+      "loss": 0.3971,
+      "step": 50
+    },
+    {
+      "epoch": 0.26301369863013696,
+      "grad_norm": 0.12593719363212585,
+      "learning_rate": 2.565217391304348e-05,
+      "loss": 0.2952,
+      "step": 60
+    },
+    {
+      "epoch": 0.30684931506849317,
+      "grad_norm": 0.11282460391521454,
+      "learning_rate": 3e-05,
+      "loss": 0.2592,
+      "step": 70
+    },
+    {
+      "epoch": 0.3506849315068493,
+      "grad_norm": 0.10163664072751999,
+      "learning_rate": 2.9514563106796115e-05,
+      "loss": 0.2402,
+      "step": 80
+    },
+    {
+      "epoch": 0.39452054794520547,
+      "grad_norm": 0.09871397167444229,
+      "learning_rate": 2.9029126213592237e-05,
+      "loss": 0.2251,
+      "step": 90
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 0.09532774984836578,
+      "learning_rate": 2.854368932038835e-05,
+      "loss": 0.2132,
+      "step": 100
+    },
+    {
+      "epoch": 0.4821917808219178,
+      "grad_norm": 0.08755984157323837,
+      "learning_rate": 2.8058252427184466e-05,
+      "loss": 0.2086,
+      "step": 110
+    },
+    {
+      "epoch": 0.5260273972602739,
+      "grad_norm": 0.09590521454811096,
+      "learning_rate": 2.757281553398058e-05,
+      "loss": 0.198,
+      "step": 120
+    },
+    {
+      "epoch": 0.5698630136986301,
+      "grad_norm": 0.09363297373056412,
+      "learning_rate": 2.7087378640776702e-05,
+      "loss": 0.1954,
+      "step": 130
+    },
+    {
+      "epoch": 0.6136986301369863,
+      "grad_norm": 0.09872984886169434,
+      "learning_rate": 2.6601941747572816e-05,
+      "loss": 0.1902,
+      "step": 140
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 0.12371695041656494,
+      "learning_rate": 2.611650485436893e-05,
+      "loss": 0.1892,
+      "step": 150
+    },
+    {
+      "epoch": 0.7013698630136986,
+      "grad_norm": 0.10814935714006424,
+      "learning_rate": 2.563106796116505e-05,
+      "loss": 0.1808,
+      "step": 160
+    },
+    {
+      "epoch": 0.7452054794520548,
+      "grad_norm": 0.12739220261573792,
+      "learning_rate": 2.5145631067961167e-05,
+      "loss": 0.1815,
+      "step": 170
+    },
+    {
+      "epoch": 0.7890410958904109,
+      "grad_norm": 0.1482655555009842,
+      "learning_rate": 2.466019417475728e-05,
+      "loss": 0.1652,
+      "step": 180
+    },
+    {
+      "epoch": 0.8328767123287671,
+      "grad_norm": 0.13323327898979187,
+      "learning_rate": 2.41747572815534e-05,
+      "loss": 0.1663,
+      "step": 190
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.1497439742088318,
+      "learning_rate": 2.3689320388349514e-05,
+      "loss": 0.1693,
+      "step": 200
+    },
+    {
+      "epoch": 0.9205479452054794,
+      "grad_norm": 0.16727504134178162,
+      "learning_rate": 2.3203883495145632e-05,
+      "loss": 0.1588,
+      "step": 210
+    },
+    {
+      "epoch": 0.9643835616438357,
+      "grad_norm": 0.159692645072937,
+      "learning_rate": 2.2718446601941746e-05,
+      "loss": 0.1489,
+      "step": 220
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.22333618998527527,
+      "eval_runtime": 65.6094,
+      "eval_samples_per_second": 18.808,
+      "eval_steps_per_second": 9.404,
+      "step": 229
+    },
+    {
+      "epoch": 1.0043835616438357,
+      "grad_norm": 0.18387436866760254,
+      "learning_rate": 2.2233009708737864e-05,
+      "loss": 0.1542,
+      "step": 230
+    },
+    {
+      "epoch": 1.0482191780821917,
+      "grad_norm": 0.17115731537342072,
+      "learning_rate": 2.1747572815533982e-05,
+      "loss": 0.1419,
+      "step": 240
+    },
+    {
+      "epoch": 1.0920547945205479,
+      "grad_norm": 0.20462283492088318,
+      "learning_rate": 2.1262135922330097e-05,
+      "loss": 0.1291,
+      "step": 250
+    },
+    {
+      "epoch": 1.135890410958904,
+      "grad_norm": 0.21275432407855988,
+      "learning_rate": 2.0776699029126215e-05,
+      "loss": 0.1345,
+      "step": 260
+    },
+    {
+      "epoch": 1.1797260273972603,
+      "grad_norm": 0.19069133698940277,
+      "learning_rate": 2.029126213592233e-05,
+      "loss": 0.1304,
+      "step": 270
+    },
+    {
+      "epoch": 1.2235616438356165,
+      "grad_norm": 0.23898746073246002,
+      "learning_rate": 1.9805825242718447e-05,
+      "loss": 0.1286,
+      "step": 280
+    },
+    {
+      "epoch": 1.2673972602739725,
+      "grad_norm": 0.22382740676403046,
+      "learning_rate": 1.9320388349514565e-05,
+      "loss": 0.1257,
+      "step": 290
+    },
+    {
+      "epoch": 1.3112328767123287,
+      "grad_norm": 0.21581463515758514,
+      "learning_rate": 1.883495145631068e-05,
+      "loss": 0.1075,
+      "step": 300
+    },
+    {
+      "epoch": 1.355068493150685,
+      "grad_norm": 0.20519264042377472,
+      "learning_rate": 1.8349514563106795e-05,
+      "loss": 0.114,
+      "step": 310
+    },
+    {
+      "epoch": 1.398904109589041,
+      "grad_norm": 0.24191145598888397,
+      "learning_rate": 1.7864077669902913e-05,
+      "loss": 0.1084,
+      "step": 320
+    },
+    {
+      "epoch": 1.4427397260273973,
+      "grad_norm": 0.2942422032356262,
+      "learning_rate": 1.737864077669903e-05,
+      "loss": 0.1169,
+      "step": 330
+    },
+    {
+      "epoch": 1.4865753424657533,
+      "grad_norm": 0.29472362995147705,
+      "learning_rate": 1.6893203883495145e-05,
+      "loss": 0.1048,
+      "step": 340
+    },
+    {
+      "epoch": 1.5304109589041097,
+      "grad_norm": 0.27294427156448364,
+      "learning_rate": 1.6407766990291263e-05,
+      "loss": 0.104,
+      "step": 350
+    },
+    {
+      "epoch": 1.5742465753424657,
+      "grad_norm": 0.3031008243560791,
+      "learning_rate": 1.592233009708738e-05,
+      "loss": 0.1064,
+      "step": 360
+    },
+    {
+      "epoch": 1.618082191780822,
+      "grad_norm": 0.3000255227088928,
+      "learning_rate": 1.5436893203883496e-05,
+      "loss": 0.0965,
+      "step": 370
+    },
+    {
+      "epoch": 1.6619178082191781,
+      "grad_norm": 0.3417374789714813,
+      "learning_rate": 1.4951456310679612e-05,
+      "loss": 0.103,
+      "step": 380
+    },
+    {
+      "epoch": 1.705753424657534,
+      "grad_norm": 0.260896235704422,
+      "learning_rate": 1.4466019417475728e-05,
+      "loss": 0.0949,
+      "step": 390
+    },
+    {
+      "epoch": 1.7495890410958905,
+      "grad_norm": 0.3573839068412781,
+      "learning_rate": 1.3980582524271846e-05,
+      "loss": 0.1005,
+      "step": 400
+    },
+    {
+      "epoch": 1.7934246575342465,
+      "grad_norm": 0.32356780767440796,
+      "learning_rate": 1.349514563106796e-05,
+      "loss": 0.0924,
+      "step": 410
+    },
+    {
+      "epoch": 1.8372602739726027,
+      "grad_norm": 0.3374144434928894,
+      "learning_rate": 1.3009708737864079e-05,
+      "loss": 0.0962,
+      "step": 420
+    },
+    {
+      "epoch": 1.881095890410959,
+      "grad_norm": 0.30275803804397583,
+      "learning_rate": 1.2524271844660193e-05,
+      "loss": 0.098,
+      "step": 430
+    },
+    {
+      "epoch": 1.924931506849315,
+      "grad_norm": 0.2706526815891266,
+      "learning_rate": 1.2038834951456311e-05,
+      "loss": 0.093,
+      "step": 440
+    },
+    {
+      "epoch": 1.9687671232876713,
+      "grad_norm": 0.30319514870643616,
+      "learning_rate": 1.1553398058252427e-05,
+      "loss": 0.0932,
+      "step": 450
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.23950284719467163,
+      "eval_runtime": 65.404,
+      "eval_samples_per_second": 18.867,
+      "eval_steps_per_second": 9.434,
+      "step": 458
+    },
+    {
+      "epoch": 2.0087671232876714,
+      "grad_norm": 0.3190622627735138,
+      "learning_rate": 1.1067961165048544e-05,
+      "loss": 0.0796,
+      "step": 460
+    },
+    {
+      "epoch": 2.0526027397260274,
+      "grad_norm": 0.20361511409282684,
+      "learning_rate": 1.058252427184466e-05,
+      "loss": 0.0852,
+      "step": 470
+    },
+    {
+      "epoch": 2.0964383561643833,
+      "grad_norm": 0.29404351115226746,
+      "learning_rate": 1.0097087378640776e-05,
+      "loss": 0.0745,
+      "step": 480
+    },
+    {
+      "epoch": 2.1402739726027398,
+      "grad_norm": 0.2433903068304062,
+      "learning_rate": 9.611650485436894e-06,
+      "loss": 0.0793,
+      "step": 490
+    },
+    {
+      "epoch": 2.1841095890410958,
+      "grad_norm": 0.31765592098236084,
+      "learning_rate": 9.12621359223301e-06,
+      "loss": 0.086,
+      "step": 500
+    },
+    {
+      "epoch": 2.227945205479452,
+      "grad_norm": 0.28951069712638855,
+      "learning_rate": 8.640776699029127e-06,
+      "loss": 0.0814,
+      "step": 510
+    },
+    {
+      "epoch": 2.271780821917808,
+      "grad_norm": 0.3745494782924652,
+      "learning_rate": 8.155339805825243e-06,
+      "loss": 0.0856,
+      "step": 520
+    },
+    {
+      "epoch": 2.315616438356164,
+      "grad_norm": 0.2525760531425476,
+      "learning_rate": 7.66990291262136e-06,
+      "loss": 0.078,
+      "step": 530
+    },
+    {
+      "epoch": 2.3594520547945206,
+      "grad_norm": 0.2950601279735565,
+      "learning_rate": 7.1844660194174755e-06,
+      "loss": 0.0758,
+      "step": 540
+    },
+    {
+      "epoch": 2.4032876712328766,
+      "grad_norm": 0.23691079020500183,
+      "learning_rate": 6.699029126213593e-06,
+      "loss": 0.0706,
+      "step": 550
+    },
+    {
+      "epoch": 2.447123287671233,
+      "grad_norm": 0.2603223919868469,
+      "learning_rate": 6.213592233009709e-06,
+      "loss": 0.0711,
+      "step": 560
+    },
+    {
+      "epoch": 2.490958904109589,
+      "grad_norm": 0.2159614861011505,
+      "learning_rate": 5.728155339805826e-06,
+      "loss": 0.075,
+      "step": 570
+    },
+    {
+      "epoch": 2.534794520547945,
+      "grad_norm": 0.23896284401416779,
+      "learning_rate": 5.242718446601942e-06,
+      "loss": 0.0824,
+      "step": 580
+    },
+    {
+      "epoch": 2.5786301369863014,
+      "grad_norm": 0.2901216149330139,
+      "learning_rate": 4.7572815533980585e-06,
+      "loss": 0.0903,
+      "step": 590
+    },
+    {
+      "epoch": 2.6224657534246574,
+      "grad_norm": 0.29583826661109924,
+      "learning_rate": 4.271844660194175e-06,
+      "loss": 0.0796,
+      "step": 600
+    },
+    {
+      "epoch": 2.666301369863014,
+      "grad_norm": 0.3026266098022461,
+      "learning_rate": 3.7864077669902915e-06,
+      "loss": 0.0733,
+      "step": 610
+    },
+    {
+      "epoch": 2.71013698630137,
+      "grad_norm": 0.2562008202075958,
+      "learning_rate": 3.3009708737864078e-06,
+      "loss": 0.0797,
+      "step": 620
+    },
+    {
+      "epoch": 2.7539726027397258,
+      "grad_norm": 0.30706337094306946,
+      "learning_rate": 2.815533980582524e-06,
+      "loss": 0.0755,
+      "step": 630
+    },
+    {
+      "epoch": 2.797808219178082,
+      "grad_norm": 0.32250040769577026,
+      "learning_rate": 2.3300970873786407e-06,
+      "loss": 0.0717,
+      "step": 640
+    },
+    {
+      "epoch": 2.8416438356164386,
+      "grad_norm": 0.301578164100647,
+      "learning_rate": 1.8446601941747572e-06,
+      "loss": 0.0663,
+      "step": 650
+    },
+    {
+      "epoch": 2.8854794520547946,
+      "grad_norm": 0.26296401023864746,
+      "learning_rate": 1.359223300970874e-06,
+      "loss": 0.0817,
+      "step": 660
+    },
+    {
+      "epoch": 2.9293150684931506,
+      "grad_norm": 0.32804426550865173,
+      "learning_rate": 8.737864077669904e-07,
+      "loss": 0.0778,
+      "step": 670
+    },
+    {
+      "epoch": 2.9731506849315066,
+      "grad_norm": 0.3096996247768402,
+      "learning_rate": 3.883495145631068e-07,
+      "loss": 0.0776,
+      "step": 680
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2448684424161911,
+      "eval_runtime": 65.3239,
+      "eval_samples_per_second": 18.89,
+      "eval_steps_per_second": 9.445,
+      "step": 687
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 687,
+  "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": 7.379988366727496e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-687/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee7536bf82641b420fe5dff159b13045ace05d8fdb821d389fc6c8d3f91b668
+size 5841

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
+size 11421995

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee7536bf82641b420fe5dff159b13045ace05d8fdb821d389fc6c8d3f91b668
+size 5841