Upload SynthFix adapter and router

README.md

@@ -0,0 +1,55 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-7b-hf
+pipeline_tag: text-generation
+tags:
+- code
+- program-repair
+- vulnerability-repair
+- peft
+- lora
+- synthfix
+- router
+- codeflaws
+---
+
+# SynthFix CodeLlama-7b-hf (CodeFlaws)
+
+This repository contains the SynthFix LoRA repair-agent adapter and matching router checkpoint for **C functional repair** on **CodeFlaws**.
+
+SynthFix is an adaptive neuro-symbolic code repair framework. During training, a lightweight router chooses between supervised fine-tuning (SFT) and reward fine-tuning (RFT), while the reward combines compiler-, analyzer-, and test-derived symbolic evidence. At inference time, the same evidence supports best-of-K candidate selection with a greedy floor.
+
+## Contents
+
+- `adapter_model.safetensors`, `adapter_config.json`: PEFT/LoRA adapter for `codellama/CodeLlama-7b-hf`.
+- tokenizer files copied from the training checkpoint.
+- `router.pt`: PyTorch state dict for the SynthFix router associated with this adapter.
+
+## Base Model
+
+This adapter is intended to be loaded with `codellama/CodeLlama-7b-hf` using `peft.PeftModel.from_pretrained`.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = "codellama/CodeLlama-7b-hf"
+adapter_id = "CoderDoge/synthfix-codellama-7b-codeflaws"
+
+tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
+base = AutoModelForCausalLM.from_pretrained(base_model, trust_remote_code=True)
+model = PeftModel.from_pretrained(base, adapter_id)
+```
+
+The router architecture is implemented in the SynthFix artifact repository: https://github.com/CoderDoge1108/SynthFix and https://github.com/largehappygroup/SynthFix.
+
+## Paper
+
+SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair
+
+- arXiv: https://arxiv.org/abs/2604.17184
+- GitHub artifact: https://github.com/CoderDoge1108/SynthFix
+
+## Notes
+
+These are adapter weights rather than full copies of the base models. Users should follow the license and usage terms of the corresponding base model.

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296bc307c6324048a66be39116b7dd6f9e97c04a58df201f38cc14c18563e449
+size 33589040

router.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56473ad48be86548ac7ddf9934c5417cd7d5b127e81a15fcd80d2f2638b61540
+size 20478

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}