EM-PRM v2 a2_support_qwen25_s0

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,34 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+library_name: peft
+tags:
+- lora
+- process-reward-model
+- multimodal
+- chart-reasoning
+- em-prm
+---
+# EM-PRM v2 — `a2_support_qwen25_s0`
+
+LoRA adapter for **Qwen/Qwen2.5-VL-7B-Instruct** from the paper *EM-PRM: Evidence-Mediated Process Rewards for Robust Multimodal Reasoning* (EM-PRM v2 experiment ladder).
+
+A2 support checkpoint on Qwen2.5-VL-7B-Instruct (initialisation of the rung-6 arms).
+
+## Training
+- LoRA rank 64, alpha 128, dropout 0.05, target modules k_proj, layers.0.mlp.down_proj, layers.0.mlp.gate_proj, layers.0.mlp.up_proj, layers.1.mlp.down_proj, layers.1.mlp.gate_proj, layers.1.mlp.up_proj, layers.10.mlp.down_proj, layers.10.mlp.gate_proj, layers.10.mlp.up_proj, layers.11.mlp.down_proj, layers.11.mlp.gate_proj, layers.11.mlp.up_proj, layers.12.mlp.down_proj, layers.12.mlp.gate_proj, layers.12.mlp.up_proj, layers.13.mlp.down_proj, layers.13.mlp.gate_proj, layers.13.mlp.up_proj, layers.14.mlp.down_proj, layers.14.mlp.gate_proj, layers.14.mlp.up_proj, layers.15.mlp.down_proj, layers.15.mlp.gate_proj, layers.15.mlp.up_proj, layers.16.mlp.down_proj, layers.16.mlp.gate_proj, layers.16.mlp.up_proj, layers.17.mlp.down_proj, layers.17.mlp.gate_proj, layers.17.mlp.up_proj, layers.18.mlp.down_proj, layers.18.mlp.gate_proj, layers.18.mlp.up_proj, layers.19.mlp.down_proj, layers.19.mlp.gate_proj, layers.19.mlp.up_proj, layers.2.mlp.down_proj, layers.2.mlp.gate_proj, layers.2.mlp.up_proj, layers.20.mlp.down_proj, layers.20.mlp.gate_proj, layers.20.mlp.up_proj, layers.21.mlp.down_proj, layers.21.mlp.gate_proj, layers.21.mlp.up_proj, layers.22.mlp.down_proj, layers.22.mlp.gate_proj, layers.22.mlp.up_proj, layers.23.mlp.down_proj, layers.23.mlp.gate_proj, layers.23.mlp.up_proj, layers.24.mlp.down_proj, layers.24.mlp.gate_proj, layers.24.mlp.up_proj, layers.25.mlp.down_proj, layers.25.mlp.gate_proj, layers.25.mlp.up_proj, layers.26.mlp.down_proj, layers.26.mlp.gate_proj, layers.26.mlp.up_proj, layers.27.mlp.down_proj, layers.27.mlp.gate_proj, layers.27.mlp.up_proj, layers.3.mlp.down_proj, layers.3.mlp.gate_proj, layers.3.mlp.up_proj, layers.4.mlp.down_proj, layers.4.mlp.gate_proj, layers.4.mlp.up_proj, layers.5.mlp.down_proj, layers.5.mlp.gate_proj, layers.5.mlp.up_proj, layers.6.mlp.down_proj, layers.6.mlp.gate_proj, layers.6.mlp.up_proj, layers.7.mlp.down_proj, layers.7.mlp.gate_proj, layers.7.mlp.up_proj, layers.8.mlp.down_proj, layers.8.mlp.gate_proj, layers.8.mlp.up_proj, layers.9.mlp.down_proj, layers.9.mlp.gate_proj, layers.9.mlp.up_proj, o_proj, q_proj, v_proj; vision tower frozen; bfloat16.
+- Seed 0, learning rate 5e-05, effective batch 2×4, one epoch.
+- Training data, pair sets and every gate artifact are in the mirror `RESEARCH-EMPRM/emprm-v2` (dataset repo; `results/runs_v2/train/a2_support_qwen25_s0/`) and the paper bundle under `backdata/`.
+
+## Load
+```python
+from transformers import AutoModelForImageTextToText, AutoProcessor
+from peft import PeftModel
+base = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", dtype="bfloat16", device_map="cuda")
+model = PeftModel.from_pretrained(base, "RESEARCH-EMPRM/emprm-v2-a2_support_qwen25_s0")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
+```
+`adapter_config.json` records the local path the adapter was trained from; pass the base model explicitly as above. Scoring prompts (bank extraction, claim extraction, claim support, ranking) are the ones in `work/scripts/eval_bon.py` of the mirror.
+
+## Provenance
+Trained  in the EM-PRM v2 repository; every number quoted in the paper is traceable to `planning/V2_PLAN.md` and the generated tables in the mirror.

adapter_config.json

@@ -0,0 +1,127 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/NetDisk/ingyu/RESEARCH/groundedprm_shared/hf/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/cc594898137f460bfe9f0759e9844b3ce807cfb5",
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "layers.9.mlp.gate_proj",
+    "layers.11.mlp.up_proj",
+    "layers.0.mlp.gate_proj",
+    "layers.25.mlp.down_proj",
+    "layers.11.mlp.down_proj",
+    "layers.15.mlp.gate_proj",
+    "layers.5.mlp.down_proj",
+    "layers.3.mlp.up_proj",
+    "layers.25.mlp.up_proj",
+    "v_proj",
+    "layers.7.mlp.gate_proj",
+    "layers.3.mlp.gate_proj",
+    "layers.14.mlp.up_proj",
+    "layers.13.mlp.gate_proj",
+    "layers.13.mlp.down_proj",
+    "layers.26.mlp.up_proj",
+    "layers.1.mlp.up_proj",
+    "layers.4.mlp.down_proj",
+    "layers.19.mlp.gate_proj",
+    "layers.20.mlp.up_proj",
+    "layers.8.mlp.gate_proj",
+    "layers.9.mlp.up_proj",
+    "layers.17.mlp.up_proj",
+    "layers.6.mlp.down_proj",
+    "layers.27.mlp.gate_proj",
+    "layers.24.mlp.up_proj",
+    "layers.25.mlp.gate_proj",
+    "layers.18.mlp.up_proj",
+    "layers.22.mlp.up_proj",
+    "layers.26.mlp.gate_proj",
+    "layers.17.mlp.gate_proj",
+    "layers.26.mlp.down_proj",
+    "layers.5.mlp.gate_proj",
+    "layers.14.mlp.down_proj",
+    "layers.2.mlp.gate_proj",
+    "layers.23.mlp.down_proj",
+    "layers.18.mlp.gate_proj",
+    "layers.21.mlp.down_proj",
+    "layers.10.mlp.up_proj",
+    "layers.12.mlp.down_proj",
+    "layers.12.mlp.up_proj",
+    "layers.3.mlp.down_proj",
+    "layers.10.mlp.down_proj",
+    "layers.16.mlp.gate_proj",
+    "layers.2.mlp.up_proj",
+    "layers.1.mlp.gate_proj",
+    "layers.17.mlp.down_proj",
+    "layers.20.mlp.gate_proj",
+    "layers.14.mlp.gate_proj",
+    "layers.6.mlp.gate_proj",
+    "layers.7.mlp.down_proj",
+    "layers.24.mlp.down_proj",
+    "layers.13.mlp.up_proj",
+    "layers.15.mlp.down_proj",
+    "layers.9.mlp.down_proj",
+    "layers.0.mlp.up_proj",
+    "layers.22.mlp.down_proj",
+    "o_proj",
+    "layers.4.mlp.gate_proj",
+    "layers.8.mlp.up_proj",
+    "layers.16.mlp.down_proj",
+    "layers.4.mlp.up_proj",
+    "layers.7.mlp.up_proj",
+    "layers.8.mlp.down_proj",
+    "layers.12.mlp.gate_proj",
+    "layers.0.mlp.down_proj",
+    "q_proj",
+    "layers.27.mlp.down_proj",
+    "layers.21.mlp.gate_proj",
+    "layers.23.mlp.gate_proj",
+    "layers.20.mlp.down_proj",
+    "layers.22.mlp.gate_proj",
+    "layers.1.mlp.down_proj",
+    "layers.21.mlp.up_proj",
+    "layers.10.mlp.gate_proj",
+    "k_proj",
+    "layers.27.mlp.up_proj",
+    "layers.23.mlp.up_proj",
+    "layers.2.mlp.down_proj",
+    "layers.24.mlp.gate_proj",
+    "layers.6.mlp.up_proj",
+    "layers.18.mlp.down_proj",
+    "layers.15.mlp.up_proj",
+    "layers.11.mlp.gate_proj",
+    "layers.16.mlp.up_proj",
+    "layers.19.mlp.up_proj",
+    "layers.19.mlp.down_proj",
+    "layers.5.mlp.up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6b155cba56aa0a6de1bdfeef78a2a07d715c2d9d43444c7c0a203e29a1da67
+size 645981584

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

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": "<|im_end|>",
+    "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 sha256:2e216950deae1db8809a180cb70673d51865b431e131bffe2db78c1c1d1269a7
+size 11422163

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}