Upload refined_adapters

.gitattributes

@@ -33,3 +33,12 @@ 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
+cpp/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+csharp/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+java/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+php/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+python/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+rust/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+shell/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+swift/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+typescript/tokenizer.json filter=lfs diff=lfs merge=lfs -text

cpp/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

cpp/adapter_config.json

@@ -0,0 +1,141 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.8.self_attn.v_pr",
+    "model.layers.13.self_attn.q_pr",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.5.self_attn.q_pr",
+    "model.layers.15.self_attn.v_pr",
+    "model.layers.14.self_attn.v_pr",
+    "model.layers.25.self_attn.k_pr",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.13.self_attn.k_pr",
+    "model.layers.24.self_attn.k_pr",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.26.self_attn.v_pr",
+    "model.layers.26.self_attn.q_pr",
+    "model.layers.20.self_attn.q_pr",
+    "model.layers.7.self_attn.k_pr",
+    "model.layers.6.self_attn.v_pr",
+    "model.layers.23.self_attn.q_pr",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.25.self_attn.q_pr",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.14.self_attn.k_pr",
+    "model.layers.26.self_attn.k_pr",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.9.self_attn.v_pr",
+    "model.layers.11.self_attn.q_pr",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.10.self_attn.k_pr",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.10.self_attn.v_pr",
+    "model.layers.9.self_attn.q_pr",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.27.self_attn.v_pr",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.4.self_attn.k_pr",
+    "model.layers.15.self_attn.k_pr",
+    "model.layers.12.self_attn.v_pr",
+    "model.layers.24.self_attn.v_pr",
+    "model.layers.7.self_attn.q_pr",
+    "model.layers.8.self_attn.k_pr",
+    "model.layers.11.self_attn.v_pr",
+    "model.layers.17.self_attn.v_pr",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.21.self_attn.v_pr",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.6.self_attn.q_pr",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.13.self_attn.v_pr",
+    "model.layers.17.self_attn.q_pr",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.11.self_attn.k_pr",
+    "model.layers.19.self_attn.v_pr",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.15.self_attn.q_pr",
+    "model.layers.19.self_attn.q_pr",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.16.self_attn.v_pr",
+    "model.layers.17.self_attn.k_pr",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.16.self_attn.k_pr",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.21.self_attn.k_pr",
+    "model.layers.5.self_attn.k_pr",
+    "model.layers.5.self_attn.v_pr",
+    "model.layers.10.self_attn.q_pr",
+    "model.layers.22.self_attn.q_pr",
+    "model.layers.6.self_attn.k_pr",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.12.self_attn.q_pr",
+    "model.layers.9.self_attn.k_pr",
+    "model.layers.8.self_attn.q_pr",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.23.self_attn.v_pr",
+    "model.layers.4.self_attn.v_pr",
+    "model.layers.22.self_attn.v_pr",
+    "model.layers.22.self_attn.k_pr",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.27.self_attn.q_pr",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.18.self_attn.v_pr",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.12.self_attn.k_pr",
+    "model.layers.23.self_attn.k_pr",
+    "model.layers.24.self_attn.q_pr",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.27.self_attn.k_pr",
+    "model.layers.19.self_attn.k_pr",
+    "model.layers.20.self_attn.v_pr",
+    "model.layers.20.self_attn.k_pr",
+    "model.layers.18.self_attn.q_pr",
+    "model.layers.16.self_attn.q_pr",
+    "model.layers.7.self_attn.v_pr",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.14.self_attn.q_pr",
+    "model.layers.21.self_attn.q_pr",
+    "model.layers.25.self_attn.v_pr",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.4.self_attn.q_pr",
+    "model.layers.18.self_attn.k_pr",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.20.self_attn.v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

cpp/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3710bdc78410b16d3c5ada25b6997a5ccfd8a97ef95aa7cf8539411facd3511e
+size 3751635

cpp/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
+}

cpp/refine.log

@@ -0,0 +1,31 @@
+
+============================================================
+Refinement started at 2026-06-14 23:57:58
+============================================================
+Logging to ./refined_adapters/cpp/refine.log
+Args: Namespace(language='cpp', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/cpp', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_cpp', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/cpp/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 96 pairs (skipped: 72 no-fail-traceback, 229 no-label)
+[refine] 96 repair pairs for language=cpp
+Time to load fused_adam op: 1.4614949226379395 seconds
+***** Running adapter refinement *****
+  language      = cpp
+  train pairs   = 96
+  epochs        = 3
+  steps/epoch   = 12
+  total steps   = 36
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/12 global_step 5 loss 0.1551
+[epoch 1/3] step 10/12 global_step 10 loss 0.1509
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 3/12 global_step 15 loss 0.1093
+[epoch 2/3] step 8/12 global_step 20 loss 0.1210
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 1/12 global_step 25 loss 0.1935
+[epoch 3/3] step 6/12 global_step 30 loss 0.1063
+[epoch 3/3] step 11/12 global_step 35 loss 0.0987
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/cpp

cpp/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|endoftext|>",
+  "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
+  }
+}

cpp/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0059fe6ae581a08561f5f94a4221fd44b7ada9154886d34daffc6e5fb8843905
+size 11421994

cpp/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

csharp/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

csharp/adapter_config.json

@@ -0,0 +1,141 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.21.self_attn.q_pr",
+    "model.layers.27.self_attn.k_pr",
+    "model.layers.4.self_attn.v_pr",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.22.self_attn.v_pr",
+    "model.layers.14.self_attn.q_pr",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.5.self_attn.q_pr",
+    "model.layers.6.self_attn.k_pr",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.15.self_attn.q_pr",
+    "model.layers.9.self_attn.v_pr",
+    "model.layers.15.self_attn.v_pr",
+    "model.layers.16.self_attn.v_pr",
+    "model.layers.9.self_attn.k_pr",
+    "model.layers.11.self_attn.q_pr",
+    "model.layers.23.self_attn.v_pr",
+    "model.layers.22.self_attn.q_pr",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.13.self_attn.q_pr",
+    "model.layers.10.self_attn.q_pr",
+    "model.layers.15.self_attn.k_pr",
+    "model.layers.17.self_attn.v_pr",
+    "model.layers.18.self_attn.v_pr",
+    "model.layers.7.self_attn.k_pr",
+    "model.layers.7.self_attn.v_pr",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.24.self_attn.k_pr",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.13.self_attn.k_pr",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.6.self_attn.v_pr",
+    "model.layers.21.self_attn.v_pr",
+    "model.layers.4.self_attn.q_pr",
+    "model.layers.20.self_attn.q_pr",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.6.self_attn.q_pr",
+    "model.layers.22.self_attn.k_pr",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.13.self_attn.v_pr",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.26.self_attn.v_pr",
+    "model.layers.7.self_attn.q_pr",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.16.self_attn.q_pr",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.12.self_attn.v_pr",
+    "model.layers.20.self_attn.k_pr",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.12.self_attn.k_pr",
+    "model.layers.23.self_attn.q_pr",
+    "model.layers.10.self_attn.v_pr",
+    "model.layers.21.self_attn.k_pr",
+    "model.layers.25.self_attn.k_pr",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.24.self_attn.q_pr",
+    "model.layers.18.self_attn.q_pr",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.19.self_attn.v_pr",
+    "model.layers.23.self_attn.k_pr",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.8.self_attn.v_pr",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.20.self_attn.v_pr",
+    "model.layers.9.self_attn.q_pr",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.4.self_attn.k_pr",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.5.self_attn.v_pr",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.18.self_attn.k_pr",
+    "model.layers.25.self_attn.q_pr",
+    "model.layers.14.self_attn.v_pr",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.8.self_attn.k_pr",
+    "model.layers.17.self_attn.q_pr",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.12.self_attn.q_pr",
+    "model.layers.24.self_attn.v_pr",
+    "model.layers.26.self_attn.k_pr",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.27.self_attn.q_pr",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.19.self_attn.k_pr",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.8.self_attn.q_pr",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.5.self_attn.k_pr",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.17.self_attn.k_pr",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.11.self_attn.v_pr",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.26.self_attn.q_pr",
+    "model.layers.10.self_attn.k_pr",
+    "model.layers.16.self_attn.k_pr",
+    "model.layers.19.self_attn.q_pr",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.14.self_attn.k_pr",
+    "model.layers.25.self_attn.v_pr",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.27.self_attn.v_pr",
+    "model.layers.11.self_attn.k_pr"
+  ],
+  "task_type": "CAUSAL_LM"
+}

csharp/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39e6b36dd7424e1c07081c34c353d993f22bdab55719e16d208431dabc60724
+size 3751635

csharp/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
+}

csharp/refine.log

@@ -0,0 +1,30 @@
+
+============================================================
+Refinement started at 2026-06-15 00:07:12
+============================================================
+Logging to ./refined_adapters/csharp/refine.log
+Args: Namespace(language='csharp', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/csharp', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_csharp', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/csharp/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 75 pairs (skipped: 124 no-fail-traceback, 187 no-label)
+[refine] 75 repair pairs for language=csharp
+Time to load fused_adam op: 1.1044878959655762 seconds
+***** Running adapter refinement *****
+  language      = csharp
+  train pairs   = 75
+  epochs        = 3
+  steps/epoch   = 10
+  total steps   = 30
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/10 global_step 5 loss 0.1979
+[epoch 1/3] step 10/10 global_step 10 loss 0.3009
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 5/10 global_step 15 loss 0.1282
+[epoch 2/3] step 10/10 global_step 20 loss 0.0966
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 5/10 global_step 25 loss 0.1390
+[epoch 3/3] step 10/10 global_step 30 loss 0.1243
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/csharp

csharp/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|endoftext|>",
+  "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
+  }
+}

csharp/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0059fe6ae581a08561f5f94a4221fd44b7ada9154886d34daffc6e5fb8843905
+size 11421994

csharp/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

java/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

java/adapter_config.json

@@ -0,0 +1,141 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.6.self_attn.k_pr",
+    "model.layers.7.self_attn.v_pr",
+    "model.layers.17.self_attn.q_pr",
+    "model.layers.10.self_attn.q_pr",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.17.self_attn.k_pr",
+    "model.layers.10.self_attn.v_pr",
+    "model.layers.12.self_attn.q_pr",
+    "model.layers.27.self_attn.v_pr",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.16.self_attn.q_pr",
+    "model.layers.22.self_attn.k_pr",
+    "model.layers.11.self_attn.v_pr",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.4.self_attn.q_pr",
+    "model.layers.22.self_attn.q_pr",
+    "model.layers.9.self_attn.k_pr",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.21.self_attn.v_pr",
+    "model.layers.9.self_attn.q_pr",
+    "model.layers.9.self_attn.v_pr",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.18.self_attn.v_pr",
+    "model.layers.27.self_attn.k_pr",
+    "model.layers.23.self_attn.k_pr",
+    "model.layers.19.self_attn.k_pr",
+    "model.layers.4.self_attn.v_pr",
+    "model.layers.15.self_attn.v_pr",
+    "model.layers.15.self_attn.q_pr",
+    "model.layers.8.self_attn.v_pr",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.5.self_attn.v_pr",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.14.self_attn.v_pr",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.19.self_attn.q_pr",
+    "model.layers.27.self_attn.q_pr",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.26.self_attn.q_pr",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.22.self_attn.v_pr",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.26.self_attn.v_pr",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.8.self_attn.k_pr",
+    "model.layers.13.self_attn.v_pr",
+    "model.layers.17.self_attn.v_pr",
+    "model.layers.24.self_attn.v_pr",
+    "model.layers.4.self_attn.k_pr",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.14.self_attn.q_pr",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.23.self_attn.v_pr",
+    "model.layers.7.self_attn.q_pr",
+    "model.layers.24.self_attn.q_pr",
+    "model.layers.16.self_attn.v_pr",
+    "model.layers.7.self_attn.k_pr",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.5.self_attn.k_pr",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.21.self_attn.q_pr",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.18.self_attn.q_pr",
+    "model.layers.20.self_attn.q_pr",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.18.self_attn.k_pr",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.12.self_attn.v_pr",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.16.self_attn.k_pr",
+    "model.layers.11.self_attn.q_pr",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.8.self_attn.q_pr",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.15.self_attn.k_pr",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.12.self_attn.k_pr",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.26.self_attn.k_pr",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.6.self_attn.q_pr",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.5.self_attn.q_pr",
+    "model.layers.23.self_attn.q_pr",
+    "model.layers.25.self_attn.q_pr",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.10.self_attn.k_pr",
+    "model.layers.19.self_attn.v_pr",
+    "model.layers.6.self_attn.v_pr",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.13.self_attn.q_pr",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.11.self_attn.k_pr",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.25.self_attn.k_pr",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.21.self_attn.k_pr",
+    "model.layers.14.self_attn.k_pr",
+    "model.layers.25.self_attn.v_pr",
+    "model.layers.13.self_attn.k_pr",
+    "model.layers.24.self_attn.k_pr",
+    "model.layers.20.self_attn.v_pr",
+    "model.layers.20.self_attn.k_pr"
+  ],
+  "task_type": "CAUSAL_LM"
+}

java/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407a666092f94fff04508e7b04fa7b36b307a39395030e20fdb851a7ebf13988
+size 3751635

java/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
+}

java/refine.log

@@ -0,0 +1,27 @@
+
+============================================================
+Refinement started at 2026-06-15 00:09:33
+============================================================
+Logging to ./refined_adapters/java/refine.log
+Args: Namespace(language='java', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/java', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_java', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/java/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 39 pairs (skipped: 62 no-fail-traceback, 285 no-label)
+[refine] 39 repair pairs for language=java
+Time to load fused_adam op: 1.475332498550415 seconds
+***** Running adapter refinement *****
+  language      = java
+  train pairs   = 39
+  epochs        = 3
+  steps/epoch   = 5
+  total steps   = 15
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/5 global_step 5 loss 0.1334
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 5/5 global_step 10 loss 0.1796
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 5/5 global_step 15 loss 0.1711
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/java

java/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|endoftext|>",
+  "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
+  }
+}

java/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0059fe6ae581a08561f5f94a4221fd44b7ada9154886d34daffc6e5fb8843905
+size 11421994

java/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

php/README.md

@@ -0,0 +1,206 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

php/adapter_config.json

@@ -0,0 +1,141 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.18.self_attn.k_pr",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.27.self_attn.k_pr",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.7.self_attn.v_pr",
+    "model.layers.26.self_attn.q_pr",
+    "model.layers.10.self_attn.k_pr",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.23.self_attn.q_pr",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.13.self_attn.q_pr",
+    "model.layers.6.self_attn.q_pr",
+    "model.layers.4.self_attn.k_pr",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.15.self_attn.v_pr",
+    "model.layers.7.self_attn.q_pr",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.22.self_attn.k_pr",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.9.self_attn.k_pr",
+    "model.layers.9.self_attn.v_pr",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.8.self_attn.k_pr",
+    "model.layers.13.self_attn.k_pr",
+    "model.layers.11.self_attn.v_pr",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.25.self_attn.k_pr",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.12.self_attn.k_pr",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.10.self_attn.q_pr",
+    "model.layers.18.self_attn.q_pr",
+    "model.layers.15.self_attn.k_pr",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.5.self_attn.k_pr",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.16.self_attn.v_pr",
+    "model.layers.8.self_attn.v_pr",
+    "model.layers.25.self_attn.v_pr",
+    "model.layers.19.self_attn.v_pr",
+    "model.layers.20.self_attn.q_pr",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.24.self_attn.k_pr",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.15.self_attn.q_pr",
+    "model.layers.17.self_attn.q_pr",
+    "model.layers.17.self_attn.v_pr",
+    "model.layers.21.self_attn.q_pr",
+    "model.layers.10.self_attn.v_pr",
+    "model.layers.27.self_attn.v_pr",
+    "model.layers.14.self_attn.k_pr",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.16.self_attn.k_pr",
+    "model.layers.23.self_attn.k_pr",
+    "model.layers.24.self_attn.v_pr",
+    "model.layers.20.self_attn.v_pr",
+    "model.layers.4.self_attn.q_pr",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.21.self_attn.k_pr",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.26.self_attn.k_pr",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.22.self_attn.q_pr",
+    "model.layers.25.self_attn.q_pr",
+    "model.layers.7.self_attn.k_pr",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.27.self_attn.q_pr",
+    "model.layers.16.self_attn.q_pr",
+    "model.layers.5.self_attn.q_pr",
+    "model.layers.19.self_attn.q_pr",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.13.self_attn.v_pr",
+    "model.layers.23.self_attn.v_pr",
+    "model.layers.14.self_attn.q_pr",
+    "model.layers.26.self_attn.v_pr",
+    "model.layers.18.self_attn.v_pr",
+    "model.layers.6.self_attn.v_pr",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.17.self_attn.k_pr",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.12.self_attn.v_pr",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.11.self_attn.k_pr",
+    "model.layers.22.self_attn.v_pr",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.21.self_attn.v_pr",
+    "model.layers.24.self_attn.q_pr",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.11.self_attn.q_pr",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.12.self_attn.q_pr",
+    "model.layers.20.self_attn.k_pr",
+    "model.layers.9.self_attn.q_pr",
+    "model.layers.19.self_attn.k_pr",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.14.self_attn.v_pr",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.4.self_attn.v_pr",
+    "model.layers.5.self_attn.v_pr",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.6.self_attn.k_pr",
+    "model.layers.8.self_attn.q_pr",
+    "model.layers.26.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

php/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:112f5740ec461ca32eeab3f6699f68d9e1ebcb7fed882fbe9d7dd677404c3ab8
+size 3751635

php/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
+}

php/refine.log

@@ -0,0 +1,49 @@
+
+============================================================
+Refinement started at 2026-06-15 00:11:12
+============================================================
+Logging to ./refined_adapters/php/refine.log
+Args: Namespace(language='php', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/php', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_php', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/php/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 71 pairs (skipped: 173 no-fail-traceback, 153 no-label)
+[refine] 71 repair pairs for language=php
+Time to load fused_adam op: 1.5054538249969482 seconds
+***** Running adapter refinement *****
+  language      = php
+  train pairs   = 71
+  epochs        = 3
+  steps/epoch   = 9
+  total steps   = 27
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+
+============================================================
+Refinement started at 2026-06-15 00:43:20
+============================================================
+Logging to ./refined_adapters/php/refine.log
+Args: Namespace(language='php', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/php', per_device_train_batch_size=2, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_php', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/php/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 71 pairs (skipped: 173 no-fail-traceback, 153 no-label)
+[refine] 71 repair pairs for language=php
+Time to load fused_adam op: 0.715233325958252 seconds
+***** Running adapter refinement *****
+  language      = php
+  train pairs   = 71
+  epochs        = 3
+  steps/epoch   = 9
+  total steps   = 27
+  batch/device  = 2
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/9 global_step 5 loss 0.1939
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 1/9 global_step 10 loss 0.1830
+[epoch 2/3] step 6/9 global_step 15 loss 0.1421
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 2/9 global_step 20 loss 0.2657
+[epoch 3/3] step 7/9 global_step 25 loss 0.1668
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/php

php/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|endoftext|>",
+  "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
+  }
+}

php/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0059fe6ae581a08561f5f94a4221fd44b7ada9154886d34daffc6e5fb8843905
+size 11421994

php/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

python/README.md

@@ -0,0 +1,213 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+---
+
+# 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]
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.2

python/adapter_config.json

@@ -0,0 +1,141 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.25.self_attn.v_pr",
+    "model.layers.22.self_attn.q_pr",
+    "model.layers.10.self_attn.k_pr",
+    "model.layers.19.self_attn.q_pr",
+    "model.layers.9.self_attn.v_pr",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.25.self_attn.q_pr",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.8.self_attn.k_pr",
+    "model.layers.8.self_attn.v_pr",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.8.self_attn.q_pr",
+    "model.layers.18.self_attn.q_pr",
+    "model.layers.23.self_attn.k_pr",
+    "model.layers.6.self_attn.q_pr",
+    "model.layers.17.self_attn.v_pr",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.18.self_attn.v_pr",
+    "model.layers.16.self_attn.v_pr",
+    "model.layers.23.self_attn.q_pr",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.13.self_attn.v_pr",
+    "model.layers.24.self_attn.v_pr",
+    "model.layers.20.self_attn.q_pr",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.11.self_attn.v_pr",
+    "model.layers.9.self_attn.q_pr",
+    "model.layers.13.self_attn.k_pr",
+    "model.layers.4.self_attn.q_pr",
+    "model.layers.26.self_attn.q_pr",
+    "model.layers.26.self_attn.k_pr",
+    "model.layers.12.self_attn.k_pr",
+    "model.layers.19.self_attn.v_pr",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.24.self_attn.k_pr",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.11.self_attn.k_pr",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.12.self_attn.q_pr",
+    "model.layers.5.self_attn.q_pr",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.7.self_attn.q_pr",
+    "model.layers.15.self_attn.v_pr",
+    "model.layers.21.self_attn.v_pr",
+    "model.layers.4.self_attn.v_pr",
+    "model.layers.15.self_attn.k_pr",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.17.self_attn.q_pr",
+    "model.layers.10.self_attn.q_pr",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.21.self_attn.k_pr",
+    "model.layers.14.self_attn.k_pr",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.6.self_attn.v_pr",
+    "model.layers.15.self_attn.q_pr",
+    "model.layers.21.self_attn.q_pr",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.16.self_attn.q_pr",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.19.self_attn.k_pr",
+    "model.layers.9.self_attn.k_pr",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.4.self_attn.k_pr",
+    "model.layers.18.self_attn.k_pr",
+    "model.layers.20.self_attn.k_pr",
+    "model.layers.22.self_attn.k_pr",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.27.self_attn.v_pr",
+    "model.layers.25.self_attn.k_pr",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.12.self_attn.v_pr",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.5.self_attn.v_pr",
+    "model.layers.14.self_attn.q_pr",
+    "model.layers.11.self_attn.q_pr",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.27.self_attn.q_pr",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.22.self_attn.v_pr",
+    "model.layers.27.self_attn.k_pr",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.14.self_attn.v_pr",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.7.self_attn.v_pr",
+    "model.layers.16.self_attn.k_pr",
+    "model.layers.23.self_attn.v_pr",
+    "model.layers.24.self_attn.q_pr",
+    "model.layers.17.self_attn.k_pr",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.7.self_attn.k_pr",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.26.self_attn.v_pr",
+    "model.layers.20.self_attn.v_pr",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.6.self_attn.k_pr",
+    "model.layers.13.self_attn.q_pr",
+    "model.layers.5.self_attn.k_pr",
+    "model.layers.10.self_attn.v_pr"
+  ],
+  "task_type": "CAUSAL_LM"
+}

python/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496df47b764ce06c00e0aa9f72d9f3034b283563ed40523010f310e7d187f7dd
+size 3751635

python/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
+}

python/refine.log

@@ -0,0 +1,73 @@
+
+============================================================
+Refinement started at 2026-06-14 06:18:05
+============================================================
+Logging to ./refined_adapters/python/refine.log
+Args: Namespace(language='python', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/python', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=1024, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_python', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/python/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 195 pairs (skipped: 231 no-fail-traceback, 0 no-label)
+[refine] 195 repair pairs for language=python
+Time to load fused_adam op: 1.9950942993164062 seconds
+***** Running adapter refinement *****
+  language      = python
+  train pairs   = 195
+  epochs        = 3
+  steps/epoch   = 17
+  total steps   = 51
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/17 global_step 5 loss 0.5386
+[epoch 1/3] step 10/17 global_step 10 loss 0.4107
+[epoch 1/3] step 15/17 global_step 15 loss 0.5793
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 3/17 global_step 20 loss 0.4969
+[epoch 2/3] step 8/17 global_step 25 loss 0.5477
+[epoch 2/3] step 13/17 global_step 30 loss 0.7573
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 1/17 global_step 35 loss 0.5654
+[epoch 3/3] step 6/17 global_step 40 loss 0.4474
+[epoch 3/3] step 11/17 global_step 45 loss 0.5370
+[epoch 3/3] step 16/17 global_step 50 loss 0.3835
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/python
+
+============================================================
+Refinement started at 2026-06-14 23:53:30
+============================================================
+Logging to ./refined_adapters/python/refine.log
+Args: Namespace(language='python', results_dir='ankhanhtran02/executed_calibration_results', results_source='hf_hub', results_repo_type='model', adapter_path='ankhanhtran02/lora-per-task-executable-start-4', model_name_or_path='Qwen/Qwen2.5-Coder-1.5B', output_dir='./refined_adapters/python', per_device_train_batch_size=4, num_train_epochs=3, learning_rate=5e-05, weight_decay=0.01, gradient_accumulation_steps=4, num_warmup_steps=0, max_prompt_len=1024, max_ans_len=2048, seed=42, logging_steps=5, local_rank=0, offload=False, zero_stage=0, gradient_checkpointing=False, disable_dropout=False, run_name='refine_python', group_name='refine_adapter', enable_wandb=False, enable_tensorboard=False, tensorboard_path='refine_tensorboard', deepspeed=True, deepspeed_config=None, deepscale=False, deepscale_config=None, global_rank=0)
+[refine] Loaded adapter from HF Hub: ankhanhtran02/lora-per-task-executable-start-4/python/0
+trainable params: 1,867,776 || all params: 1,545,176,576 || trainable%: 0.1208778355180036
+[repair] extracted 195 pairs (skipped: 231 no-fail-traceback, 0 no-label)
+[refine] 195 repair pairs for language=python
+Time to load fused_adam op: 1.7055249214172363 seconds
+***** Running adapter refinement *****
+  language      = python
+  train pairs   = 195
+  epochs        = 3
+  steps/epoch   = 25
+  total steps   = 75
+  batch/device  = 4
+  grad accum    = 4
+  lr            = 5e-05
+[epoch 1/3] step 5/25 global_step 5 loss 0.5697
+[epoch 1/3] step 10/25 global_step 10 loss 0.3202
+[epoch 1/3] step 15/25 global_step 15 loss 0.3142
+[epoch 1/3] step 20/25 global_step 20 loss 0.6230
+[epoch 1/3] step 25/25 global_step 25 loss 0.3026
+[refine] Epoch 1/3 complete.
+[epoch 2/3] step 5/25 global_step 30 loss 0.5361
+[epoch 2/3] step 10/25 global_step 35 loss 0.5786
+[epoch 2/3] step 15/25 global_step 40 loss 0.3814
+[epoch 2/3] step 20/25 global_step 45 loss 0.6810
+[epoch 2/3] step 25/25 global_step 50 loss 0.2489
+[refine] Epoch 2/3 complete.
+[epoch 3/3] step 5/25 global_step 55 loss 0.2804
+[epoch 3/3] step 10/25 global_step 60 loss 0.3424
+[epoch 3/3] step 15/25 global_step 65 loss 0.7264
+[epoch 3/3] step 20/25 global_step 70 loss 0.3545
+[epoch 3/3] step 25/25 global_step 75 loss 0.4598
+[refine] Epoch 3/3 complete.
+[refine] Saved fine-tuned adapter to ./refined_adapters/python

python/special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "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": "<|endoftext|>",
+  "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
+  }
+}

python/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0059fe6ae581a08561f5f94a4221fd44b7ada9154886d34daffc6e5fb8843905
+size 11421994

python/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "fast_tokenizer": true,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}