Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+grpo/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo-hard/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+sft/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,173 @@
 ---
-license: apache-2.0
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- peft
+- lora
+- text-to-sql
+- sql
+- sft
+- grpo
+- rlvr
+- trl
 ---
+
+# SQL-R1
+
+SQL-R1 trains Qwen3-4B-Base for complex Text-to-SQL through completion-only
+supervised fine-tuning and GRPO with verifiable SQLite execution feedback.
+
+This repository contains three LoRA adapters:
+
+| Subfolder | Stage | Intended use |
+|---|---|---|
+| `sft` | Completion-only SFT | Supervised baseline |
+| `grpo` | SFT + execution-feedback GRPO | Recommended main checkpoint |
+| `grpo-hard` | Hard-sample curriculum GRPO | Ablation and analysis |
+
+All three adapters require
+[`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base).
+
+## Results
+
+Execution accuracy (EX) and execution-valid rate were evaluated on the complete
+public BIRD Dev and Spider Dev splits using a consistent greedy-decoding and
+SQLite-execution pipeline.
+
+| Checkpoint | BIRD Dev EX | BIRD execution-valid | Spider Dev EX | Spider execution-valid |
+|---|---:|---:|---:|---:|
+| Qwen3-4B-Base | 23.21% | 55.61% | 55.51% | 77.66% |
+| `sft` | 42.37% | 87.29% | 77.27% | 96.62% |
+| **`grpo`** | **42.37%** | 87.35% | **79.59%** | 97.00% |
+| `grpo-hard` | 42.50% | **88.79%** | 78.92% | **97.20%** |
+
+The `grpo` checkpoint improves Spider Dev EX by 2.32 percentage points over
+SFT while preserving BIRD Dev EX. The curriculum ablation improves BIRD
+execution validity but shows mild Spider forgetting.
+
+These are project-side development-set measurements rather than hidden-test
+leaderboard submissions. Systems using database-content retrieval,
+self-consistency, reranking, or larger proprietary models are not directly
+comparable.
+
+## Training overview
+
+### SFT
+
+- Training records: 12,976
+- Validation records: 608
+- Completion-only loss: prompt tokens are masked and loss is computed only on
+  the target SQL
+- LoRA rank/alpha/dropout: 32 / 64 / 0.05
+- Trainable parameters: 66.1M (1.62%)
+- Precision: BF16
+
+### GRPO
+
+- RL training records: 12,885
+- Optimization steps: 300
+- Candidates per prompt: 4
+- Approximate generated rollouts: 1,200
+- Reward signals: SQL validity, read-only safety, executability, and execution
+  result equivalence
+- Parallel read-only SQLite rollout validation
+
+Gold SQL and execution results are available only to the reward function and
+are never included in the model prompt.
+
+### Hard-sample curriculum ablation
+
+- Curriculum records: 2,522
+- BIRD moderate/challenging focus records: 1,891
+- Stratified replay records: 631
+- Optimization steps: 300
+- Validation database overlap: 0
+
+## Usage
+
+Choose one of `sft`, `grpo`, or `grpo-hard`. The recommended default is `grpo`.
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base_model_id = "Qwen/Qwen3-4B-Base"
+repo_id = "j2521402/SQL-R1"
+adapter_subfolder = "grpo"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(
+    base_model,
+    repo_id,
+    subfolder=adapter_subfolder,
+).eval()
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You are a Text-to-SQL assistant. Given a SQLite database schema, "
+            "optional evidence, and a question, return exactly one read-only "
+            "SQLite query. Do not include explanations or Markdown fences."
+        ),
+    },
+    {
+        "role": "user",
+        "content": (
+            'Database schema:\nTABLE "singer" ("Singer_ID" INT, "Name" TEXT);\n\n'
+            "Question:\nHow many singers do we have?"
+        ),
+    },
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+).to(model.device)
+
+with torch.inference_mode():
+    output = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        do_sample=False,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+
+completion = output[0, inputs["input_ids"].shape[1]:]
+print(tokenizer.decode(completion, skip_special_tokens=True).strip())
+```
+
+Each subfolder also contains its tokenizer configuration and detailed model
+card.
+
+## Limitations
+
+- Training and evaluation focus on English Text-to-SQL and SQLite.
+- Prompts contain database schemas and optional evidence but do not
+  automatically retrieve database contents.
+- Execution equivalence is a strong but imperfect correctness signal.
+- Generated SQL may still be wrong or expensive. Execute it only in a
+  read-only sandbox with time and row limits.
+- SQL-R1 is a direct Text-to-SQL model, not a general tool-calling agent.
+
+## Code
+
+Data processing, SFT, GRPO reward, training, and evaluation code:
+[j2521402/SQL-R1](https://github.com/j2521402/SQL-R1).
+

grpo-hard/README.md

@@ -0,0 +1,116 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- peft
+- lora
+- text-to-sql
+- sql
+- grpo
+- rlvr
+- curriculum-learning
+- trl
+---
+
+# SQL-R1-GRPO-Hard
+
+SQL-R1-GRPO-Hard is a curriculum-learning ablation of SQL-R1. It continues
+GRPO training from SQL-R1-GRPO on BIRD moderate and challenging examples mixed
+with stratified replay data.
+
+This repository contains a LoRA adapter for
+[`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base).
+For the best overall balance across BIRD and Spider, use SQL-R1-GRPO; this
+checkpoint is published primarily for analysis and reproducibility.
+
+## Curriculum data
+
+- Total records: 2,522
+- BIRD moderate/challenging focus records: 1,891
+- Stratified replay records: 631
+- Spider replay records: 316
+- Validation database overlap: 0
+
+The replay subset preserves easier examples and cross-dataset coverage while
+the curriculum emphasizes harder BIRD queries.
+
+## Training
+
+- Starting checkpoint: SQL-R1-GRPO
+- Optimization steps: 300
+- Candidates per prompt: 4
+- Approximate generated rollouts: 1,200
+- Learning rate: 2e-6
+- Precision: BF16
+- Reward: SQL validity, read-only safety, executability, and result equivalence
+  under parallel SQLite execution
+
+Gold SQL is used only to compute verifiable execution rewards and is never
+included in the model prompt.
+
+## Evaluation
+
+| Checkpoint | BIRD Dev EX | BIRD execution-valid | Spider Dev EX | Spider execution-valid |
+|---|---:|---:|---:|---:|
+| SQL-R1-GRPO | 42.37% | 87.35% | **79.59%** | 97.00% |
+| **SQL-R1-GRPO-Hard** | **42.50%** | **88.79%** | 78.92% | **97.20%** |
+
+Hard-sample curriculum training slightly improves BIRD execution accuracy and
+execution validity, but Spider EX decreases mildly. This result illustrates the
+specialization–retention trade-off and motivates the replay ablation.
+
+These are project-side measurements on the complete public development splits,
+not hidden-test leaderboard submissions.
+
+## Usage
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base_model_id = "Qwen/Qwen3-4B-Base"
+repo_id = "j2521402/SQL-R1"
+adapter_subfolder = "grpo-hard"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(
+    model,
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+model.eval()
+```
+
+Use the same SQL-only ChatML prompt format documented in the
+[SQL-R1 repository](https://github.com/j2521402/SQL-R1).
+
+## Limitations
+
+- This checkpoint deliberately specializes toward harder BIRD examples and
+  shows mild Spider forgetting.
+- Training and evaluation focus on English Text-to-SQL and SQLite.
+- Database contents are not automatically retrieved for the prompt.
+- Generated SQL should be executed only in a read-only sandbox with resource
+  limits.
+- This is an ablation checkpoint rather than the recommended general model.
+
+## Project
+
+Training, curriculum-data construction, reward, and evaluation code:
+[j2521402/SQL-R1](https://github.com/j2521402/SQL-R1).
+
+Core libraries: PyTorch 2.8.0, Transformers 5.14.1, PEFT 0.19.1,
+TRL 1.8.0, Datasets 5.0.0, and Accelerate 1.14.0.

grpo-hard/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

grpo-hard/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438f3b22fb4c1ac3a2ef0b416378b9196350c702a343be836c59906e6e74c782
+size 264308896

grpo-hard/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

grpo-hard/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

grpo-hard/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

grpo/README.md

@@ -0,0 +1,157 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- peft
+- lora
+- text-to-sql
+- sql
+- grpo
+- rlvr
+- trl
+---
+
+# SQL-R1-GRPO
+
+SQL-R1-GRPO is the main SQL-R1 checkpoint: a LoRA adapter trained on
+Qwen3-4B-Base with completion-only supervised fine-tuning followed by GRPO
+using verifiable SQLite execution feedback.
+
+The model receives a database schema, optional evidence, and a natural-language
+question, then generates one read-only SQLite query. This repository contains
+the adapter only; load it together with
+[`Qwen/Qwen3-4B-Base`](https://huggingface.co/Qwen/Qwen3-4B-Base).
+
+## Training
+
+GRPO starts from the SQL-R1-SFT adapter and optimizes generated SQL with a
+layered execution reward:
+
+| Outcome | Reward |
+|---|---:|
+| Empty output | -1.00 |
+| Invalid or non-read-only SQL | -0.75 |
+| SQL execution error | -0.25 |
+| Truncated execution result | -0.10 |
+| Executable but incorrect result | +0.25 |
+| Execution-equivalent to the gold query | +1.00 |
+
+A low-weight format reward additionally encourages concise SQL-only output.
+Gold SQL and gold execution results are used only by the reward function and
+are never included in the model prompt.
+
+- RL training records: 12,885
+- Optimization steps: 300
+- Candidates per prompt: 4
+- Approximate generated rollouts: 1,200
+- Learning rate: 5e-6
+- GRPO beta: 0.001
+- Clipping epsilon: 0.2
+- Precision: BF16
+- Execution backend: parallel read-only SQLite workers
+
+## Evaluation
+
+Execution accuracy (EX) and execution-valid rate were measured on the complete
+BIRD Dev and Spider Dev splits with the same greedy decoding and execution
+pipeline at every stage.
+
+| Checkpoint | BIRD Dev EX | BIRD execution-valid | Spider Dev EX | Spider execution-valid |
+|---|---:|---:|---:|---:|
+| SQL-R1-SFT | 42.37% | 87.29% | 77.27% | 96.62% |
+| **SQL-R1-GRPO** | **42.37%** | **87.35%** | **79.59%** | **97.00%** |
+
+GRPO improves Spider Dev EX by 2.32 percentage points over SFT while preserving
+BIRD Dev EX. This is the recommended SQL-R1 checkpoint.
+
+These numbers are project-side development-set measurements, not hidden-test
+leaderboard submissions. Results from systems using prompting, database
+contents, self-consistency, reranking, or larger proprietary models are not
+directly comparable.
+
+## Usage
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base_model_id = "Qwen/Qwen3-4B-Base"
+repo_id = "j2521402/SQL-R1"
+adapter_subfolder = "grpo"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(
+    model,
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+model.eval()
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You are a Text-to-SQL assistant. Given a SQLite database schema, "
+            "optional evidence, and a question, return exactly one read-only "
+            "SQLite query. Do not include explanations or Markdown fences."
+        ),
+    },
+    {
+        "role": "user",
+        "content": (
+            'Database schema:\nTABLE "singer" ("Singer_ID" INT, "Name" TEXT);\n\n'
+            "Question:\nHow many singers do we have?"
+        ),
+    },
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+).to(model.device)
+
+with torch.inference_mode():
+    output = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        do_sample=False,
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.pad_token_id,
+    )
+
+completion = output[0, inputs["input_ids"].shape[1]:]
+print(tokenizer.decode(completion, skip_special_tokens=True).strip())
+```
+
+## Limitations
+
+- Training and evaluation focus on English Text-to-SQL and SQLite.
+- Prompts contain database schemas and optional evidence, but do not perform
+  automatic database-content retrieval.
+- Execution equivalence is a strong but imperfect semantic correctness signal.
+- The model may still generate incorrect or expensive queries; execute outputs
+  in a read-only sandbox with time and row limits.
+- This is a direct Text-to-SQL model, not a general tool-calling agent.
+
+## Project
+
+Training, data processing, reward, and evaluation code:
+[j2521402/SQL-R1](https://github.com/j2521402/SQL-R1).
+
+Core libraries: PyTorch 2.8.0, Transformers 5.14.1, PEFT 0.19.1,
+TRL 1.8.0, Datasets 5.0.0, and Accelerate 1.14.0.

grpo/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

grpo/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41bba278ef202b1431372a22a953cc79cba80a0d8aa348733b62bd8f6bbaa1f
+size 264308896

grpo/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

grpo/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

grpo/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

sft/README.md

@@ -0,0 +1,144 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- peft
+- lora
+- text-to-sql
+- sql
+- supervised-fine-tuning
+---
+
+# SQL-R1-SFT
+
+SQL-R1-SFT is a LoRA adapter for
+[Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base), trained to
+translate a SQLite schema, optional evidence, and a natural-language question
+into exactly one read-only SQL query.
+
+This is an adapter-only repository. The Qwen3-4B-Base weights are required for
+inference.
+
+## Training
+
+- **Method:** completion-only supervised fine-tuning
+- **Training data:** filtered BIRD and Spider training examples
+- **Records:** 12,976 train / 608 database-disjoint validation
+- **LoRA:** rank 32, alpha 64, dropout 0.05
+- **Target modules:** all attention and MLP projections
+- **Trainable parameters:** 66.1M (1.62%)
+- **Precision:** BF16
+- **Epochs:** 1
+- **Learning rate:** 1e-4
+- **Effective batch size:** 16
+
+Only target SQL tokens contribute to the loss. Schema, evidence, and question
+tokens are masked. The final assistant completion uses Qwen3-4B-Base's native
+`<|endoftext|>` EOS rather than the ChatML turn separator.
+
+## Evaluation
+
+Execution accuracy (EX) and execution-valid rate were measured with a common
+read-only SQLite evaluator on the public development sets.
+
+| Model | BIRD Dev EX | BIRD valid | Spider Dev EX | Spider valid |
+|---|---:|---:|---:|---:|
+| Qwen3-4B-Base | 23.21% | 55.61% | 55.51% | 77.66% |
+| SQL-R1-SFT | **42.37%** | **87.29%** | **77.27%** | **96.62%** |
+
+These are public Dev results produced by the SQL-R1 evaluator, not official
+hidden-test leaderboard submissions.
+
+## Usage
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base_id = "Qwen/Qwen3-4B-Base"
+repo_id = "j2521402/SQL-R1"
+adapter_subfolder = "sft"
+
+tokenizer = AutoTokenizer.from_pretrained(
+    repo_id,
+    subfolder=adapter_subfolder,
+)
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(
+    base_model,
+    repo_id,
+    subfolder=adapter_subfolder,
+).eval()
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You are a Text-to-SQL assistant. Given a SQLite database schema, "
+            "optional evidence, and a question, return exactly one read-only "
+            "SQLite query. Do not include explanations or Markdown fences."
+        ),
+    },
+    {
+        "role": "user",
+        "content": (
+            'Database schema:\nTABLE "singer" ("id" INT, "name" TEXT);\n\n'
+            "Question:\nHow many singers are there?"
+        ),
+    },
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    enable_thinking=False,
+    return_dict=True,
+    return_tensors="pt",
+).to(model.device)
+
+with torch.inference_mode():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=512,
+        do_sample=False,
+        eos_token_id=[
+            tokenizer.eos_token_id,
+            tokenizer.convert_tokens_to_ids("<|im_end|>"),
+        ],
+    )
+
+sql = tokenizer.decode(
+    outputs[0, inputs["input_ids"].shape[1]:],
+    skip_special_tokens=True,
+).strip()
+print(sql)
+```
+
+## Limitations
+
+- Training and evaluation target SQLite and English Text-to-SQL benchmarks.
+- Prompts contain schema metadata but not database row contents.
+- The adapter does not implement tool calling or an autonomous SQL agent.
+- Generated SQL should be validated and executed through a read-only,
+  resource-limited database connection.
+
+## Project
+
+Training code, preprocessing, evaluator, and reproducibility details:
+[j2521402/SQL-R1](https://github.com/j2521402/SQL-R1).
+
+### Framework versions
+
+- PyTorch 2.8.0+cu128
+- Transformers 5.14.1
+- PEFT 0.19.1

sft/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

sft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9fa60097d34eb3844ad134e2edb29fa6db7ba901a39505936cc15d971fd9af
+size 264308896

sft/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

sft/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

sft/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}