Keep only standard model assets and documentation

Follow the Qwen2.5-Omni-3B model repository layout: remove auxiliary training, evaluation, and release manifests. Retain checkpoint assets, model card, license, and the required derivative notice.

Notice

@@ -11,4 +11,4 @@ Modified weight files relative to the upstream pretrained model:
   model-00004-of-00005.safetensors
   model-00005-of-00005.safetensors
 
-These shards are byte-identical to the evaluated AudioJev checkpoint. The model/configuration and shard layout were saved by the training pipeline. The release corrects the optional total_parameters index metadata to the number of elements actually stored; tensor data and the weight map are unchanged. README.md, training_recipe.json, evaluation_results.json and release_manifest.json document this derivative. Inference software is maintained separately in AudioJev-Inference.
+These shards are byte-identical to the evaluated AudioJev checkpoint. The model/configuration and shard layout were saved by the training pipeline. The release corrects the optional total_parameters index metadata to the number of elements actually stored; tensor data and the weight map are unchanged. README.md documents this derivative. Inference software is maintained separately in AudioJev-Inference.

README.md

@@ -38,13 +38,13 @@ AudioJev takes an audio waveform, a natural-language question, and a list of can
 | Recommended inference dtype | BF16 |
 | Candidate labels | `0`–`9`, then `A`–`Z` (2–36 candidates) |
 
-The audio encoder and language-model decision path were trained without a LoRA adapter. The visual branch was excluded from training; audio generation is disabled. This repository contains the complete saved Thinker checkpoint and its processor/tokenizer files. The weight shards are byte-identical to the evaluated checkpoint; hashes and release metadata are provided in `release_manifest.json`.
+The audio encoder and language-model decision path were trained without a LoRA adapter. The visual branch was excluded from training; audio generation is disabled. This repository contains the complete saved Thinker checkpoint and its processor/tokenizer files. The weight shards are byte-identical to the evaluated checkpoint.
 
 For each training example, RD-SKL supervises the original candidate order and a random derangement. The second distribution is aligned by candidate identity before applying symmetric KL. Inference uses one forward pass in the supplied candidate order.
 
 ## Inference
 
-Python inference, the HTTP service, installation dependencies, and runnable examples are maintained in the standalone **AudioJev-Inference** project. This model repository distributes the model weights, tokenizer/processor assets, model documentation, and release metadata.
+Python inference, the HTTP service, installation dependencies, and runnable examples are maintained in the standalone **AudioJev-Inference** project. This model repository distributes the model weights, tokenizer/processor assets, model card, and license files.
 
 After installing AudioJev-Inference, start the service with:
 
@@ -66,7 +66,7 @@ The following scores are for **this single checkpoint in the original candidate
 | MMAR | 1,000 | 56.30% |
 | MMSU evaluated short-audio subset | 3,931 | 62.45% |
 
-`evaluation_results.json` records exact counts and values from the completed evaluation. The experiment's source audit found 119 hidden MMAU questions with audio-source overlap against general-stage fitting/development data; the official full score retains all questions. That score should be interpreted with this overlap in mind.
+The experiment's source audit found 119 hidden MMAU questions with audio-source overlap against general-stage fitting/development data; the official full score retains all questions. That score should be interpreted with this overlap in mind.
 
 ## Scope
 

evaluation_results.json

@@ -1,37 +0,0 @@
-{
-  "training_seed": 20261001,
-  "skl_weight": 0.5,
-  "candidate_order": "native",
-  "aggregation": "single checkpoint; not a seed average",
-  "metrics": {
-    "mmau_full": {
-      "questions": 10000,
-      "correct": 6941,
-      "accuracy": 0.6941
-    },
-    "mmau": {
-      "questions": 9000,
-      "correct": 6230,
-      "accuracy": 0.6922222222222222
-    },
-    "mmau_mini": {
-      "questions": 1000,
-      "correct": 711,
-      "accuracy": 0.711
-    },
-    "mmar": {
-      "questions": 1000,
-      "correct": 563,
-      "accuracy": 0.563
-    },
-    "mmsu": {
-      "questions": 3931,
-      "correct": 2455,
-      "accuracy": 0.6245230221317731
-    }
-  },
-  "mmau_scoring": "1000 public questions plus 9000 questions scored by the official service",
-  "mmsu_scope": "3931 questions in the evaluated short-audio subset",
-  "source_overlap_note": "The experiment reports 119 hidden MMAU questions whose audio sources overlap general-stage fitting/development data. Full scores retain them.",
-  "source_report_sha256": "dc53decb9db340a6b4b995b6ba475e23af09fcbe9e1cd091325fe1a6219ad5e3"
-}

release_manifest.json

@@ -1,111 +0,0 @@
-{
-  "model_name": "AudioJev",
-  "repo_id": "shlv/AudioJev",
-  "created_utc": "2026-09-28T16:06:42.633063+00:00",
-  "training_seed": 20261001,
-  "skl_weight": 0.5,
-  "checkpoint": "general/checkpoint-2048",
-  "total_training_updates": 4096,
-  "weight_shards_unchanged": true,
-  "stored_tensor_parameters": 4703464448,
-  "stored_tensor_dtypes": {
-    "F32": 4703464448
-  },
-  "index_metadata_correction": {
-    "original_total_parameters": 1519790592,
-    "actual_total_parameters": 4703464448
-  },
-  "source_index_sha256": "7ab45af26aa38dd632422333408a6dfea16c180d9fc5d382cfd1a7999b58a502",
-  "files": {
-    "LICENSE": {
-      "size": 7387,
-      "sha256": "ae8ef9d3fb476f735d9b9abeaab73b7f778b121c77427cd918ec3da01eefbc44"
-    },
-    "Notice": {
-      "size": 1211,
-      "sha256": "8ad741a5ad2d7c46d7eba46772e2dead6c627ab383dacbb1ecd7ef152a56b3ac"
-    },
-    "README.md": {
-      "size": 4992,
-      "sha256": "527dd557d508e9a52d147a8bd0709c9ddd7a6f27ff8bdc65d3d382bd9616538d"
-    },
-    "added_tokens.json": {
-      "size": 579,
-      "sha256": "e81a2cc3bd867a1217019eed202d1d8a07e1063ece716f22060dda14f6cc07d8"
-    },
-    "chat_template.jinja": {
-      "size": 1281,
-      "sha256": "d027e14db2e64eb2c23597240d42ea747b4fd5efd6e6a7604a990949c610f79c"
-    },
-    "config.json": {
-      "size": 16911,
-      "sha256": "08755783271e6c0f425fa705bccb85ae6e0b2c3db4ce904b576fb385f6d7811f"
-    },
-    "evaluation_results.json": {
-      "size": 1090,
-      "sha256": "9ce7bd97ff76bfc0dd297e9ff75c5269528b501513ba4e44d2bd3684167301d6"
-    },
-    "generation_config.json": {
-      "size": 69,
-      "sha256": "3ee3cbe9acb55059b37a4e90bb843812eb86f70c5ebea404f137cd9c80127870"
-    },
-    "merges.txt": {
-      "size": 1671853,
-      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5"
-    },
-    "model-00001-of-00005.safetensors": {
-      "size": 3995066200,
-      "sha256": "435a6fbfe7c120119b86076831c2c48542f5018c227d3cfc0856a210d351bf3b"
-    },
-    "model-00002-of-00005.safetensors": {
-      "size": 3926509296,
-      "sha256": "3087437831e84d8430707b4a3be2dca239af4049b0f944f76f6062721b9c89c0"
-    },
-    "model-00003-of-00005.safetensors": {
-      "size": 3917844848,
-      "sha256": "35b3a36a2d092b19a0427c016c8d28cea4a4e0b5f3dcf59934b7d74eded521af"
-    },
-    "model-00004-of-00005.safetensors": {
-      "size": 3917844920,
-      "sha256": "dbf98c2f42746b10be25de4087fd65935415bacd1853c7a911ebac9e153cec3a"
-    },
-    "model-00005-of-00005.safetensors": {
-      "size": 3056764904,
-      "sha256": "ebd56db24da75a8b4fc022f2f2e6dbc75a4e7995d8c140be2d69289ce9c07390"
-    },
-    "model.safetensors.index.json": {
-      "size": 127717,
-      "sha256": "6ac3736c9a2d653b21c98a41e82e963eae26008d362b9328cd1efe4427896fdb"
-    },
-    "preprocessor_config.json": {
-      "size": 667,
-      "sha256": "b47055ce61463ce143e9aab741d55c0aa520801a0a5d63be73c5b17cecb6bc69"
-    },
-    "special_tokens_map.json": {
-      "size": 833,
-      "sha256": "db7fd39f5dc9ee37998c3ed04e3a3386989182a550064d2a2a9af16822cf22f4"
-    },
-    "spk_dict.pt": {
-      "size": 259544,
-      "sha256": "6a05609b28f5d42b7b748f0f07592545c8f1f6885b9ae8fff64baf56e86b2a18"
-    },
-    "tokenizer_config.json": {
-      "size": 5181,
-      "sha256": "d2705fa47e1aecad75e3ac83ca42ec983d47bd48e9c740791ebf2c005922704b"
-    },
-    "training_recipe.json": {
-      "size": 2551,
-      "sha256": "9ea8795d0ff10e5c94042d9fd22a4305101abbddc53968cefd1267242e0d5d52"
-    },
-    "video_preprocessor_config.json": {
-      "size": 1229,
-      "sha256": "3e7254028ff085aa9e0322c2db0f2b86781fb186d1d690ad4e990eb01fd466c2"
-    },
-    "vocab.json": {
-      "size": 3383407,
-      "sha256": "87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d"
-    }
-  },
-  "layout_updated_utc": "2026-09-28T16:34:03.104869+00:00",
-  "inference_project": "AudioJev-Inference"
-}

training_recipe.json

@@ -1,61 +0,0 @@
-{
-  "model_name": "AudioJev",
-  "base_model": "Qwen/Qwen2.5-Omni-3B",
-  "seed": 20261001,
-  "skl_weight": 0.5,
-  "method": "random_derangement_skl",
-  "loss": "paired_candidate_ce_plus_aligned_skl",
-  "pair_kind": "random",
-  "max_prompt_tokens": 4096,
-  "stages": [
-    {
-      "name": "semantic",
-      "learning_rate": 1e-06,
-      "warmup_steps": 32,
-      "eval_every": 256,
-      "examples": 4096,
-      "steps": 1024,
-      "development_examples": 256,
-      "ordered_train_sha256": "a9bd81622009a8b3ac0703eebdc9aeedd47c0c40e13403a3551fd83478210d50",
-      "source_train_sha256": "dcce30c0f53fd226f626ab9e55962671bbb5c82104f99de20e830c74c2fcdc74",
-      "development_sha256": "d6514e47cb62896de71c1418320106f32f997dc4e0ea68284b3784d861428368"
-    },
-    {
-      "name": "joint",
-      "learning_rate": 1e-06,
-      "warmup_steps": 32,
-      "eval_every": 256,
-      "examples": 4096,
-      "steps": 1024,
-      "development_examples": 320,
-      "ordered_train_sha256": "22d9fc5a9722b69363f1d614375d396af76e39e95c80ab8a0dec0af9bf949f9d",
-      "source_train_sha256": "7393eb4bb002ad2810d06c520f08e52eeca5feddb60becc1c58b9b826da06c19",
-      "development_sha256": "1af43e24f729f29be82b8229d341336a7a0a66549ffe0756dca0d7d172fe9172"
-    },
-    {
-      "name": "general",
-      "learning_rate": 1e-06,
-      "warmup_steps": 32,
-      "eval_every": 512,
-      "examples": 8192,
-      "steps": 2048,
-      "development_examples": 576,
-      "ordered_train_sha256": "5c2ae98a4a57bef65f77a43c8329ec9d9015d4b7b10094485d73380dc90c2842",
-      "source_train_sha256": "c6803170e0a5cee9f978f22e562855ca2ca37240475b823bf1efa22e2b13247d",
-      "development_sha256": "5bb427425dc64822e35cda72b270b7bfd3bb3d2fb1405c6edaa5a610a6a43c45"
-    }
-  ],
-  "completed_training_updates": 4096,
-  "final_stage": "general",
-  "final_stage_step": 2048,
-  "checkpoint_choice": "fixed_final_step",
-  "checkpoint_selection_uses_development": false,
-  "checkpoint_selection_uses_test": false,
-  "hyperparameter_note": "Lambda 0.5 was chosen after the weight-comparison experiments; the fixed-step statement describes checkpoint selection only.",
-  "weights_dtype": "float32",
-  "evaluated_compute_dtype": "bfloat16",
-  "candidate_labels": "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ",
-  "probability_readout": "softmax over supplied candidate-label logits at the final input position",
-  "evaluation_plan_sha256": "c00a67288c7f49b59891ce6bbcc69352f8f8895be0ea49f27627b207cee053b1",
-  "checkpoint_metadata_sha256": "81c2e6c0ac8d1a033f37c74e143ec1a704623891eb6ac5b83a41950f7677e094"
-}