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-244/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-732/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": "./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": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "down_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:febde24122a0924479b6fe9bfcd256c1b4fe56f75da4606a0d220145309e660e
+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-244/README.md

@@ -0,0 +1,207 @@
+---
+base_model: ./Qwen2.5-Coder-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./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-244/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./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": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-244/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:febde24122a0924479b6fe9bfcd256c1b4fe56f75da4606a0d220145309e660e
+size 161533192

checkpoint-244/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-244/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-244/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed18da109a5e99c79a28a5a2b9ad2edfabb880fafc4c5ee2151b90919451f64f
+size 323296891

checkpoint-244/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97de5f00525ce4dbb7290c5a5941509287cf460b8d017186e33d1f44a4f8161f
+size 14645

checkpoint-244/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fcc9e3e46bf3e9d465607afbe1cc1a2f549f296432bfa54eefe1eccbcffb46
+size 1465

checkpoint-244/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-244/tokenizer.json

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

checkpoint-244/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-244/trainer_state.json

@@ -0,0 +1,210 @@
+{
+  "best_global_step": 244,
+  "best_metric": 0.241361603140831,
+  "best_model_checkpoint": "lora_qwen7b_java_abdiff_v2/checkpoint-244",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 244,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041109969167523124,
+      "grad_norm": 0.17571452260017395,
+      "learning_rate": 3.648648648648649e-06,
+      "loss": 0.5537,
+      "step": 10
+    },
+    {
+      "epoch": 0.08221993833504625,
+      "grad_norm": 0.12462153285741806,
+      "learning_rate": 7.702702702702703e-06,
+      "loss": 0.5427,
+      "step": 20
+    },
+    {
+      "epoch": 0.12332990750256938,
+      "grad_norm": 0.13460873067378998,
+      "learning_rate": 1.1756756756756757e-05,
+      "loss": 0.5255,
+      "step": 30
+    },
+    {
+      "epoch": 0.1644398766700925,
+      "grad_norm": 0.2371131032705307,
+      "learning_rate": 1.5810810810810808e-05,
+      "loss": 0.4849,
+      "step": 40
+    },
+    {
+      "epoch": 0.20554984583761562,
+      "grad_norm": 0.2611907720565796,
+      "learning_rate": 1.9864864864864866e-05,
+      "loss": 0.3981,
+      "step": 50
+    },
+    {
+      "epoch": 0.24665981500513876,
+      "grad_norm": 0.10762301832437515,
+      "learning_rate": 2.3918918918918917e-05,
+      "loss": 0.3275,
+      "step": 60
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.06910783052444458,
+      "learning_rate": 2.7972972972972975e-05,
+      "loss": 0.2976,
+      "step": 70
+    },
+    {
+      "epoch": 0.328879753340185,
+      "grad_norm": 0.10020674765110016,
+      "learning_rate": 2.9772036474164135e-05,
+      "loss": 0.2958,
+      "step": 80
+    },
+    {
+      "epoch": 0.3699897225077081,
+      "grad_norm": 0.06338030099868774,
+      "learning_rate": 2.9316109422492404e-05,
+      "loss": 0.2775,
+      "step": 90
+    },
+    {
+      "epoch": 0.41109969167523125,
+      "grad_norm": 0.06356582045555115,
+      "learning_rate": 2.886018237082067e-05,
+      "loss": 0.2671,
+      "step": 100
+    },
+    {
+      "epoch": 0.4522096608427544,
+      "grad_norm": 0.06176166608929634,
+      "learning_rate": 2.8404255319148935e-05,
+      "loss": 0.273,
+      "step": 110
+    },
+    {
+      "epoch": 0.4933196300102775,
+      "grad_norm": 0.0641980841755867,
+      "learning_rate": 2.7948328267477204e-05,
+      "loss": 0.2708,
+      "step": 120
+    },
+    {
+      "epoch": 0.5344295991778006,
+      "grad_norm": 0.060578711330890656,
+      "learning_rate": 2.7492401215805473e-05,
+      "loss": 0.2492,
+      "step": 130
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.07500634342432022,
+      "learning_rate": 2.7036474164133738e-05,
+      "loss": 0.2516,
+      "step": 140
+    },
+    {
+      "epoch": 0.6166495375128469,
+      "grad_norm": 0.06346568465232849,
+      "learning_rate": 2.6580547112462007e-05,
+      "loss": 0.2423,
+      "step": 150
+    },
+    {
+      "epoch": 0.65775950668037,
+      "grad_norm": 0.214496448636055,
+      "learning_rate": 2.6124620060790272e-05,
+      "loss": 0.245,
+      "step": 160
+    },
+    {
+      "epoch": 0.6988694758478932,
+      "grad_norm": 0.07425080984830856,
+      "learning_rate": 2.566869300911854e-05,
+      "loss": 0.2455,
+      "step": 170
+    },
+    {
+      "epoch": 0.7399794450154162,
+      "grad_norm": 0.08862721920013428,
+      "learning_rate": 2.521276595744681e-05,
+      "loss": 0.2377,
+      "step": 180
+    },
+    {
+      "epoch": 0.7810894141829393,
+      "grad_norm": 0.09345080703496933,
+      "learning_rate": 2.4756838905775076e-05,
+      "loss": 0.2493,
+      "step": 190
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "grad_norm": 0.12085441499948502,
+      "learning_rate": 2.4300911854103345e-05,
+      "loss": 0.243,
+      "step": 200
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.09944415092468262,
+      "learning_rate": 2.3844984802431613e-05,
+      "loss": 0.2276,
+      "step": 210
+    },
+    {
+      "epoch": 0.9044193216855088,
+      "grad_norm": 0.11600342392921448,
+      "learning_rate": 2.338905775075988e-05,
+      "loss": 0.2288,
+      "step": 220
+    },
+    {
+      "epoch": 0.9455292908530318,
+      "grad_norm": 0.11351948231458664,
+      "learning_rate": 2.2933130699088144e-05,
+      "loss": 0.2136,
+      "step": 230
+    },
+    {
+      "epoch": 0.986639260020555,
+      "grad_norm": 0.12985852360725403,
+      "learning_rate": 2.2477203647416413e-05,
+      "loss": 0.2166,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.241361603140831,
+      "eval_runtime": 48.3711,
+      "eval_samples_per_second": 13.479,
+      "eval_steps_per_second": 3.37,
+      "step": 244
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "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": 3.369854600141783e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-244/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bcb9a8b172c59bfbeb5de2996bcf34c14ab3088bcaa9e5af25d1ea7b5475fb
+size 5841

checkpoint-732/README.md

@@ -0,0 +1,207 @@
+---
+base_model: ./Qwen2.5-Coder-7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./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-732/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "./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": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-732/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18357102d6687d9803b4819244ffab68d2b8954e9560d420dcd63c63118bff0
+size 161533192

checkpoint-732/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-732/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-732/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca25eec75d6fd254d0e9dc71a8edf7480d0af60a568067daafc429ebdaa051a
+size 323296891

checkpoint-732/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:868268bc024fa29635b07c2b069ccd1c6cd0ec7ecbcb64d52ed086b9aafdfc49
+size 14645

checkpoint-732/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16a2343ff2ff3d5814c35a4c1e65910e5043b73218b0767debbef60b822176c
+size 1465

checkpoint-732/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-732/tokenizer.json

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

checkpoint-732/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-732/trainer_state.json

@@ -0,0 +1,569 @@
+{
+  "best_global_step": 244,
+  "best_metric": 0.241361603140831,
+  "best_model_checkpoint": "lora_qwen7b_java_abdiff_v2/checkpoint-244",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 732,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041109969167523124,
+      "grad_norm": 0.17571452260017395,
+      "learning_rate": 3.648648648648649e-06,
+      "loss": 0.5537,
+      "step": 10
+    },
+    {
+      "epoch": 0.08221993833504625,
+      "grad_norm": 0.12462153285741806,
+      "learning_rate": 7.702702702702703e-06,
+      "loss": 0.5427,
+      "step": 20
+    },
+    {
+      "epoch": 0.12332990750256938,
+      "grad_norm": 0.13460873067378998,
+      "learning_rate": 1.1756756756756757e-05,
+      "loss": 0.5255,
+      "step": 30
+    },
+    {
+      "epoch": 0.1644398766700925,
+      "grad_norm": 0.2371131032705307,
+      "learning_rate": 1.5810810810810808e-05,
+      "loss": 0.4849,
+      "step": 40
+    },
+    {
+      "epoch": 0.20554984583761562,
+      "grad_norm": 0.2611907720565796,
+      "learning_rate": 1.9864864864864866e-05,
+      "loss": 0.3981,
+      "step": 50
+    },
+    {
+      "epoch": 0.24665981500513876,
+      "grad_norm": 0.10762301832437515,
+      "learning_rate": 2.3918918918918917e-05,
+      "loss": 0.3275,
+      "step": 60
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.06910783052444458,
+      "learning_rate": 2.7972972972972975e-05,
+      "loss": 0.2976,
+      "step": 70
+    },
+    {
+      "epoch": 0.328879753340185,
+      "grad_norm": 0.10020674765110016,
+      "learning_rate": 2.9772036474164135e-05,
+      "loss": 0.2958,
+      "step": 80
+    },
+    {
+      "epoch": 0.3699897225077081,
+      "grad_norm": 0.06338030099868774,
+      "learning_rate": 2.9316109422492404e-05,
+      "loss": 0.2775,
+      "step": 90
+    },
+    {
+      "epoch": 0.41109969167523125,
+      "grad_norm": 0.06356582045555115,
+      "learning_rate": 2.886018237082067e-05,
+      "loss": 0.2671,
+      "step": 100
+    },
+    {
+      "epoch": 0.4522096608427544,
+      "grad_norm": 0.06176166608929634,
+      "learning_rate": 2.8404255319148935e-05,
+      "loss": 0.273,
+      "step": 110
+    },
+    {
+      "epoch": 0.4933196300102775,
+      "grad_norm": 0.0641980841755867,
+      "learning_rate": 2.7948328267477204e-05,
+      "loss": 0.2708,
+      "step": 120
+    },
+    {
+      "epoch": 0.5344295991778006,
+      "grad_norm": 0.060578711330890656,
+      "learning_rate": 2.7492401215805473e-05,
+      "loss": 0.2492,
+      "step": 130
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.07500634342432022,
+      "learning_rate": 2.7036474164133738e-05,
+      "loss": 0.2516,
+      "step": 140
+    },
+    {
+      "epoch": 0.6166495375128469,
+      "grad_norm": 0.06346568465232849,
+      "learning_rate": 2.6580547112462007e-05,
+      "loss": 0.2423,
+      "step": 150
+    },
+    {
+      "epoch": 0.65775950668037,
+      "grad_norm": 0.214496448636055,
+      "learning_rate": 2.6124620060790272e-05,
+      "loss": 0.245,
+      "step": 160
+    },
+    {
+      "epoch": 0.6988694758478932,
+      "grad_norm": 0.07425080984830856,
+      "learning_rate": 2.566869300911854e-05,
+      "loss": 0.2455,
+      "step": 170
+    },
+    {
+      "epoch": 0.7399794450154162,
+      "grad_norm": 0.08862721920013428,
+      "learning_rate": 2.521276595744681e-05,
+      "loss": 0.2377,
+      "step": 180
+    },
+    {
+      "epoch": 0.7810894141829393,
+      "grad_norm": 0.09345080703496933,
+      "learning_rate": 2.4756838905775076e-05,
+      "loss": 0.2493,
+      "step": 190
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "grad_norm": 0.12085441499948502,
+      "learning_rate": 2.4300911854103345e-05,
+      "loss": 0.243,
+      "step": 200
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.09944415092468262,
+      "learning_rate": 2.3844984802431613e-05,
+      "loss": 0.2276,
+      "step": 210
+    },
+    {
+      "epoch": 0.9044193216855088,
+      "grad_norm": 0.11600342392921448,
+      "learning_rate": 2.338905775075988e-05,
+      "loss": 0.2288,
+      "step": 220
+    },
+    {
+      "epoch": 0.9455292908530318,
+      "grad_norm": 0.11351948231458664,
+      "learning_rate": 2.2933130699088144e-05,
+      "loss": 0.2136,
+      "step": 230
+    },
+    {
+      "epoch": 0.986639260020555,
+      "grad_norm": 0.12985852360725403,
+      "learning_rate": 2.2477203647416413e-05,
+      "loss": 0.2166,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.241361603140831,
+      "eval_runtime": 48.3711,
+      "eval_samples_per_second": 13.479,
+      "eval_steps_per_second": 3.37,
+      "step": 244
+    },
+    {
+      "epoch": 1.024665981500514,
+      "grad_norm": 0.12141554057598114,
+      "learning_rate": 2.2021276595744682e-05,
+      "loss": 0.2116,
+      "step": 250
+    },
+    {
+      "epoch": 1.065775950668037,
+      "grad_norm": 0.1510457694530487,
+      "learning_rate": 2.156534954407295e-05,
+      "loss": 0.2004,
+      "step": 260
+    },
+    {
+      "epoch": 1.10688591983556,
+      "grad_norm": 0.18226052820682526,
+      "learning_rate": 2.1109422492401216e-05,
+      "loss": 0.2089,
+      "step": 270
+    },
+    {
+      "epoch": 1.1479958890030832,
+      "grad_norm": 0.1632615327835083,
+      "learning_rate": 2.0653495440729482e-05,
+      "loss": 0.1878,
+      "step": 280
+    },
+    {
+      "epoch": 1.1891058581706064,
+      "grad_norm": 0.2921697199344635,
+      "learning_rate": 2.019756838905775e-05,
+      "loss": 0.1798,
+      "step": 290
+    },
+    {
+      "epoch": 1.2302158273381294,
+      "grad_norm": 0.19414232671260834,
+      "learning_rate": 1.974164133738602e-05,
+      "loss": 0.1851,
+      "step": 300
+    },
+    {
+      "epoch": 1.2713257965056526,
+      "grad_norm": 0.2113204449415207,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.1884,
+      "step": 310
+    },
+    {
+      "epoch": 1.3124357656731758,
+      "grad_norm": 0.25703924894332886,
+      "learning_rate": 1.8829787234042554e-05,
+      "loss": 0.1666,
+      "step": 320
+    },
+    {
+      "epoch": 1.353545734840699,
+      "grad_norm": 0.32676252722740173,
+      "learning_rate": 1.837386018237082e-05,
+      "loss": 0.1673,
+      "step": 330
+    },
+    {
+      "epoch": 1.394655704008222,
+      "grad_norm": 0.2629919946193695,
+      "learning_rate": 1.7917933130699088e-05,
+      "loss": 0.1656,
+      "step": 340
+    },
+    {
+      "epoch": 1.435765673175745,
+      "grad_norm": 0.2691596448421478,
+      "learning_rate": 1.7462006079027357e-05,
+      "loss": 0.1513,
+      "step": 350
+    },
+    {
+      "epoch": 1.4768756423432683,
+      "grad_norm": 0.2598915994167328,
+      "learning_rate": 1.7006079027355622e-05,
+      "loss": 0.15,
+      "step": 360
+    },
+    {
+      "epoch": 1.5179856115107913,
+      "grad_norm": 0.2840367257595062,
+      "learning_rate": 1.655015197568389e-05,
+      "loss": 0.1393,
+      "step": 370
+    },
+    {
+      "epoch": 1.5590955806783144,
+      "grad_norm": 0.27585548162460327,
+      "learning_rate": 1.609422492401216e-05,
+      "loss": 0.1326,
+      "step": 380
+    },
+    {
+      "epoch": 1.6002055498458376,
+      "grad_norm": 0.3558744490146637,
+      "learning_rate": 1.5638297872340426e-05,
+      "loss": 0.1386,
+      "step": 390
+    },
+    {
+      "epoch": 1.6413155190133608,
+      "grad_norm": 0.3336169719696045,
+      "learning_rate": 1.5182370820668691e-05,
+      "loss": 0.135,
+      "step": 400
+    },
+    {
+      "epoch": 1.682425488180884,
+      "grad_norm": 0.4432605504989624,
+      "learning_rate": 1.4726443768996962e-05,
+      "loss": 0.1246,
+      "step": 410
+    },
+    {
+      "epoch": 1.723535457348407,
+      "grad_norm": 0.3988304138183594,
+      "learning_rate": 1.4270516717325229e-05,
+      "loss": 0.129,
+      "step": 420
+    },
+    {
+      "epoch": 1.7646454265159301,
+      "grad_norm": 0.3611379563808441,
+      "learning_rate": 1.3814589665653496e-05,
+      "loss": 0.1079,
+      "step": 430
+    },
+    {
+      "epoch": 1.8057553956834531,
+      "grad_norm": 0.4067041277885437,
+      "learning_rate": 1.3358662613981763e-05,
+      "loss": 0.1275,
+      "step": 440
+    },
+    {
+      "epoch": 1.8468653648509763,
+      "grad_norm": 0.36210691928863525,
+      "learning_rate": 1.2902735562310032e-05,
+      "loss": 0.1122,
+      "step": 450
+    },
+    {
+      "epoch": 1.8879753340184995,
+      "grad_norm": 0.3510965406894684,
+      "learning_rate": 1.2446808510638298e-05,
+      "loss": 0.0966,
+      "step": 460
+    },
+    {
+      "epoch": 1.9290853031860227,
+      "grad_norm": 0.38730406761169434,
+      "learning_rate": 1.1990881458966566e-05,
+      "loss": 0.1089,
+      "step": 470
+    },
+    {
+      "epoch": 1.9701952723535459,
+      "grad_norm": 0.39076584577560425,
+      "learning_rate": 1.1534954407294832e-05,
+      "loss": 0.1038,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.2861343026161194,
+      "eval_runtime": 48.2041,
+      "eval_samples_per_second": 13.526,
+      "eval_steps_per_second": 3.381,
+      "step": 488
+    },
+    {
+      "epoch": 2.0082219938335046,
+      "grad_norm": 0.4124261438846588,
+      "learning_rate": 1.10790273556231e-05,
+      "loss": 0.0975,
+      "step": 490
+    },
+    {
+      "epoch": 2.049331963001028,
+      "grad_norm": 0.4260999262332916,
+      "learning_rate": 1.0623100303951368e-05,
+      "loss": 0.0973,
+      "step": 500
+    },
+    {
+      "epoch": 2.090441932168551,
+      "grad_norm": 0.4411214292049408,
+      "learning_rate": 1.0167173252279635e-05,
+      "loss": 0.0803,
+      "step": 510
+    },
+    {
+      "epoch": 2.131551901336074,
+      "grad_norm": 0.5388243794441223,
+      "learning_rate": 9.711246200607902e-06,
+      "loss": 0.089,
+      "step": 520
+    },
+    {
+      "epoch": 2.172661870503597,
+      "grad_norm": 0.36110010743141174,
+      "learning_rate": 9.255319148936171e-06,
+      "loss": 0.0955,
+      "step": 530
+    },
+    {
+      "epoch": 2.21377183967112,
+      "grad_norm": 0.30860260128974915,
+      "learning_rate": 8.799392097264438e-06,
+      "loss": 0.0824,
+      "step": 540
+    },
+    {
+      "epoch": 2.2548818088386433,
+      "grad_norm": 0.42028531432151794,
+      "learning_rate": 8.343465045592705e-06,
+      "loss": 0.0936,
+      "step": 550
+    },
+    {
+      "epoch": 2.2959917780061665,
+      "grad_norm": 0.36835429072380066,
+      "learning_rate": 7.887537993920974e-06,
+      "loss": 0.074,
+      "step": 560
+    },
+    {
+      "epoch": 2.3371017471736897,
+      "grad_norm": 0.43269503116607666,
+      "learning_rate": 7.43161094224924e-06,
+      "loss": 0.0778,
+      "step": 570
+    },
+    {
+      "epoch": 2.378211716341213,
+      "grad_norm": 0.4608248770236969,
+      "learning_rate": 6.975683890577508e-06,
+      "loss": 0.0731,
+      "step": 580
+    },
+    {
+      "epoch": 2.419321685508736,
+      "grad_norm": 0.36565056443214417,
+      "learning_rate": 6.519756838905775e-06,
+      "loss": 0.0812,
+      "step": 590
+    },
+    {
+      "epoch": 2.460431654676259,
+      "grad_norm": 0.37470170855522156,
+      "learning_rate": 6.063829787234042e-06,
+      "loss": 0.071,
+      "step": 600
+    },
+    {
+      "epoch": 2.501541623843782,
+      "grad_norm": 0.47044429183006287,
+      "learning_rate": 5.607902735562311e-06,
+      "loss": 0.075,
+      "step": 610
+    },
+    {
+      "epoch": 2.542651593011305,
+      "grad_norm": 0.3516956865787506,
+      "learning_rate": 5.151975683890578e-06,
+      "loss": 0.0684,
+      "step": 620
+    },
+    {
+      "epoch": 2.5837615621788284,
+      "grad_norm": 0.4521888196468353,
+      "learning_rate": 4.696048632218845e-06,
+      "loss": 0.076,
+      "step": 630
+    },
+    {
+      "epoch": 2.6248715313463515,
+      "grad_norm": 0.45891526341438293,
+      "learning_rate": 4.240121580547112e-06,
+      "loss": 0.0701,
+      "step": 640
+    },
+    {
+      "epoch": 2.6659815005138747,
+      "grad_norm": 0.33456680178642273,
+      "learning_rate": 3.7841945288753804e-06,
+      "loss": 0.0682,
+      "step": 650
+    },
+    {
+      "epoch": 2.707091469681398,
+      "grad_norm": 0.3150039613246918,
+      "learning_rate": 3.3282674772036475e-06,
+      "loss": 0.0785,
+      "step": 660
+    },
+    {
+      "epoch": 2.7482014388489207,
+      "grad_norm": 0.3293338716030121,
+      "learning_rate": 2.872340425531915e-06,
+      "loss": 0.0634,
+      "step": 670
+    },
+    {
+      "epoch": 2.789311408016444,
+      "grad_norm": 0.37423741817474365,
+      "learning_rate": 2.4164133738601823e-06,
+      "loss": 0.0715,
+      "step": 680
+    },
+    {
+      "epoch": 2.830421377183967,
+      "grad_norm": 0.32468822598457336,
+      "learning_rate": 1.96048632218845e-06,
+      "loss": 0.0755,
+      "step": 690
+    },
+    {
+      "epoch": 2.87153134635149,
+      "grad_norm": 0.388679563999176,
+      "learning_rate": 1.5045592705167174e-06,
+      "loss": 0.0688,
+      "step": 700
+    },
+    {
+      "epoch": 2.9126413155190134,
+      "grad_norm": 0.36400821805000305,
+      "learning_rate": 1.0486322188449848e-06,
+      "loss": 0.0705,
+      "step": 710
+    },
+    {
+      "epoch": 2.9537512846865366,
+      "grad_norm": 0.34037601947784424,
+      "learning_rate": 5.927051671732523e-07,
+      "loss": 0.0647,
+      "step": 720
+    },
+    {
+      "epoch": 2.9948612538540598,
+      "grad_norm": 0.30876415967941284,
+      "learning_rate": 1.3677811550151974e-07,
+      "loss": 0.075,
+      "step": 730
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3031086027622223,
+      "eval_runtime": 48.1817,
+      "eval_samples_per_second": 13.532,
+      "eval_steps_per_second": 3.383,
+      "step": 732
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 732,
+  "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": 1.0098660093853901e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-732/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bcb9a8b172c59bfbeb5de2996bcf34c14ab3088bcaa9e5af25d1ea7b5475fb
+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 sha256:88bcb9a8b172c59bfbeb5de2996bcf34c14ab3088bcaa9e5af25d1ea7b5475fb
+size 5841