Release Fast Code Pruner

Publish the retained 82.48% F1 model, tokenizer, native vLLM package, model card, and benchmark results.

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,114 @@
+---
+license: mit
+library_name: vllm
+base_model: Qwen/Qwen2.5-Coder-0.5B
+pipeline_tag: token-classification
+tags:
+- code
+- code-pruning
+- context-pruning
+- vllm
+- qwen2
+datasets:
+- nick007x/github-code-2025
+metrics:
+- f1
+---
+
+# Fast Code Pruner
+
+Task-aware context pruning for coding agents with a 17-layer
+Qwen2.5-Coder-0.5B backbone and a native vLLM serving path.
+
+[GitHub repository](https://github.com/rotem154154/fast-code-pruner) ·
+[Original SWE-Pruner](https://github.com/Ayanami1314/swe-pruner)
+
+## Validation quality
+
+Evaluation uses the fixed 6,119-example seed-43 validation split.
+
+| Model | Accuracy ↑ | Precision ↑ | Recall ↑ | F1 ↑ |
+|---|---:|---:|---:|---:|
+| **fast-code-pruner** | **85.94%** | **81.49%** | **83.49%** | **82.48%** |
+| code-pruner | 84.07% | 80.02% | 80.91% | 80.46% |
+
+## Architecture
+
+```text
+Original Code-Pruner                         Fast Code Pruner
+
+Qwen3 layers 1–28                           Qwen2.5-Coder layers 1–17
+frozen backbone                             frozen weights + rank-8 LoRA
+          │                                           │
+hidden layers 7 + 14 + 28                   normalized hidden layer 17
+3 × 1024 → concatenate 3072                 896 → gated PolyNorm → 2432
+          │                                           │
+1× bidirectional full attention             1× bidirectional full attention
+8 heads, width 3072                         16 heads, width 2432
+          │                                           │
+CRF emissions: 3072 → 256 → 2               CRF emissions: 2432 → 128 → 2
+```
+
+Fast Code Pruner uses only the normalized final-layer representation and
+physically skips the three removed attention branches. Rank-8 LoRA updates are
+merged into dense weights during export. Prefix caching is disabled because
+the bidirectional fusion head requires the complete input.
+
+## Serving
+
+Install the native vLLM package directly from this model repository:
+
+```bash
+pip install \
+  "fast-code-pruner[vllm] @ https://huggingface.co/irotem98/fast-code-pruner/resolve/main/package/fast_code_pruner-0.1.0-py3-none-any.whl"
+fast-code-pruner serve
+```
+
+Inputs longer than 8,192 tokens are split with overlap and merged
+automatically.
+
+### Serving performance
+
+| Model | Backend | Concurrency 1 ↑ | Concurrency 16 ↑ |
+|---|---|---:|---:|
+| **fast-code-pruner** | vLLM 0.13.0 | **79.0 req/s** | **143.4 req/s** |
+| fast-code-pruner | Hugging Face | 16.01 req/s | 16.03 req/s |
+| code-pruner | Hugging Face | 9.83 req/s | 10.03 req/s |
+
+The vLLM results are medians of three 1,000-request end-to-end HTTP runs over
+the same 100 validation examples on one NVIDIA RTX PRO 6000 Blackwell Server
+Edition. Prefix caching was disabled. Median model-input throughput was 56.1k
+tokens/s at concurrency 1 and 101.8k tokens/s at concurrency 16.
+`fast-code-pruner` Hugging Face results are medians of three 100-request runs
+with an 8,192-token model length, matching the serialized legacy endpoint. The
+original `code-pruner` row uses its Hugging Face backend benchmark.
+
+## Training
+
+The public repository includes a lightweight, hard-label launcher matching the
+released architecture:
+
+```bash
+bash train/train_fast_code_pruner.sh
+```
+
+It contains no teacher-target generation or knowledge-distillation stage.
+
+## Attribution
+
+This model builds on
+[SWE-Pruner](https://github.com/Ayanami1314/swe-pruner) and
+[Qwen2.5-Coder-0.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B).
+
+```bibtex
+@misc{wang2026sweprunerselfadaptivecontextpruning,
+  title={SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents},
+  author={Yuhang Wang and Yuling Shi and Mo Yang and Rongrui Zhang and
+          Shilin He and Heng Lian and Yuting Chen and Siyu Ye and Kai Cai and
+          Xiaodong Gu},
+  year={2026},
+  eprint={2601.16746},
+  archivePrefix={arXiv},
+  primaryClass={cs.SE}
+}
+```

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
+}

benchmark_results.json

@@ -0,0 +1,80 @@
+{
+  "hardware": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
+  "validation_samples": 6119,
+  "validation_seed": 43,
+  "validation": {
+    "fast-code-pruner": {
+      "loss": 0.2731010076982715,
+      "compression_loss": 0.2731010076982715,
+      "accuracy": 0.859388530254364,
+      "precision": 0.8149362802505493,
+      "recall": 0.8348633646965027,
+      "f1": 0.8247794508934021
+    }
+  },
+  "serving": {
+    "date_utc": "2026-07-28",
+    "backend": "vLLM 0.13.0",
+    "checkpoint": "001-kd-search-weight-0.4-ac3262",
+    "requests_per_repeat": 1000,
+    "unique_validation_examples": 100,
+    "repeats": 3,
+    "prefix_caching": false,
+    "hugging_face": {
+      "requests_per_repeat": 100,
+      "warmup_requests": 10,
+      "repeats": 3,
+      "max_model_length": 8192,
+      "serialized_requests": true,
+      "concurrency_1": {
+        "requests_per_second_runs": [
+          15.635215615008196,
+          16.014152944551167,
+          16.04293924256032
+        ],
+        "requests_per_second_median": 16.014152944551167
+      },
+      "concurrency_16": {
+        "requests_per_second_runs": [
+          15.961968793509204,
+          16.049117711074377,
+          16.03105236128065
+        ],
+        "requests_per_second_median": 16.03105236128065
+      }
+    },
+    "concurrency_1": {
+      "requests_per_second_runs": [
+        77.85959605324707,
+        79.01445520339735,
+        79.55801844550992
+      ],
+      "requests_per_second_median": 79.01445520339735,
+      "model_input_tokens_per_second_median": 56078.92929150719,
+      "latency_p50_ms_median": 11.922281002625823,
+      "latency_p95_ms_median": 16.762261977419257
+    },
+    "concurrency_16": {
+      "requests_per_second_runs": [
+        139.21897948711825,
+        143.42106837168544,
+        143.6922866973871
+      ],
+      "requests_per_second_median": 143.42106837168544,
+      "model_input_tokens_per_second_median": 101790.2348554363,
+      "latency_p50_ms_median": 108.39256300823763,
+      "latency_p95_ms_median": 160.10672401171178
+    },
+    "concurrency_64": {
+      "requests_per_second_runs": [
+        172.7439921722694,
+        174.6905065239383,
+        172.40774004660466
+      ],
+      "requests_per_second_median": 172.7439921722694,
+      "model_input_tokens_per_second_median": 122601.59356442477,
+      "latency_p50_ms_median": 369.8863319878001,
+      "latency_p95_ms_median": 497.7567640016787
+    }
+  }
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "SwePrunerVllmForTokenClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 17,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 17,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936,
+  "num_labels": 3,
+  "problem_type": "regression",
+  "io_processor_plugin": "swe_pruner",
+  "swe_pruner": {
+    "bottleneck": 128,
+    "dropout": 0.1,
+    "num_fusion_layers": 1,
+    "num_heads": 16,
+    "last_layer_expansion_size": 2432,
+    "last_layer_adapter_type": "gated",
+    "last_layer_activation": "polynorm",
+    "backbone_stop_layer": 17,
+    "pruned_attention_layers": [
+      6,
+      16,
+      17
+    ],
+    "attention_type": "full",
+    "input_format": "plain_pruner",
+    "lora_merged": true,
+    "output_columns": [
+      "prune_emission",
+      "keep_emission",
+      "document_log_probability"
+    ]
+  }
+}

export_manifest.json

@@ -0,0 +1,16 @@
+{
+  "source_checkpoint": "fast-code-pruner retained seed-43 checkpoint",
+  "base_model": "Qwen/Qwen2.5-Coder-0.5B",
+  "architecture": "SwePrunerVllmForTokenClassification",
+  "merged_lora_modules": 107,
+  "pruned_attention_layers": [
+    6,
+    16,
+    17
+  ],
+  "input_format": "plain_pruner",
+  "output_contract": {
+    "token_keep_probability": "softmax(columns[0:2])[1]",
+    "document_score": "exp(last_token_column_2)"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cabcea8a8cd8ae6f55482240664e9aee9ad37ae015ec6d07463a54a98ff9ebc
+size 881711624

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}