diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..a6344aac8c09253b3b630fb776ae94478aa0275b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..da4970aa9a5404800281b28a395829fa6703c49b --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ +--- +license: mit +library_name: transformers +pipeline_tag: text-generation +--- + +# Correct Answers, Invalid Traces + +The models of *Correct Answers, Invalid Traces: What Verifiable Grade-School +Math Reveals About Chain-of-Thought Traces* (Puduppully, Misra, Iyer, Kalwar, +Palod and Kambhampati, 2026). Each is a 12-layer GPT-NeoX model (124M +parameters) trained from scratch on iGSM for 100k steps at batch 512. They differ +only in the trace that followed the problem during training. Code and the +evaluation protocol are at https://github.com/ratishsp/igsm-trace-validity. + +| folder | training trace | +|---|---| +| `clean-run-a` | minimal valid trace (the paper's main model) | +| `clean-run-b` | the same recipe, second run | +| `clean-run-c-200k` | the same recipe, 200k steps | +| `swapped` | trace of a different problem | +| `swapped-op-matched` | trace of a different problem with the same op count | +| `shuffled-10`, `-30`, `-50`, `-75`, `-100` | the first 10 to 100 percent of the trace's tokens shuffled | +| `no-trace` | answer only | +| `non-minimal` | valid trace with unnecessary steps | +| `non-minimal-90` | non-minimal for 90 percent of problems, minimal otherwise | +| `seed43/*` | seed-43 replicates of swapped, swapped-op-matched, shuffled-30 and non-minimal | + +```python +from transformers import GPTNeoXForCausalLM +model = GPTNeoXForCausalLM.from_pretrained("ratishsp/igsm-trace-validity", subfolder="clean-run-a") +``` + +The tokenizer is GPT-2's, with iGSM's special tokens 222, 223 and 224 for +`[PROB]`, `[SOL]` and `[ANS]`. `evaluate.py` in the code repository runs the +paper's evaluation on any of these folders. + +## Citation + +```bibtex +@article{puduppully2026correct, + title = {Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces}, + author = {Puduppully, Ratish and Misra, Pranabendu and Iyer, Paarth and Kalwar, Durgesh and Palod, Vardhan and Kambhampati, Subbarao}, + journal = {arXiv preprint}, + year = {2026} +} +``` diff --git a/clean-run-a/config.json b/clean-run-a/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/clean-run-a/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/clean-run-a/generation_config.json b/clean-run-a/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/clean-run-a/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/clean-run-a/model.safetensors b/clean-run-a/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8135a402828dcb22f96ccc02a84d555ae9fd63b3 --- /dev/null +++ b/clean-run-a/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b644af034089583aa0cf3567ad6ba80483507d015df939d3c0ccf24948c1a68d +size 494630368 diff --git a/clean-run-b/config.json b/clean-run-b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/clean-run-b/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/clean-run-b/generation_config.json b/clean-run-b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/clean-run-b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/clean-run-b/model.safetensors b/clean-run-b/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0957ff928889e48260e2254625d1f78cbb89e8f3 --- /dev/null +++ b/clean-run-b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfccb3a7f83c6800eaec9b23d15ae2173a694cfde0e106d712b6e44f70101036 +size 494630368 diff --git a/clean-run-c-200k/config.json b/clean-run-c-200k/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/clean-run-c-200k/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/clean-run-c-200k/generation_config.json b/clean-run-c-200k/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/clean-run-c-200k/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/clean-run-c-200k/model.safetensors b/clean-run-c-200k/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5451d2003a815f3101f72381f8a3f96c881b058b --- /dev/null +++ b/clean-run-c-200k/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359c3c632996331bf6c45cee1479887f81b9c72025800521187b0fffe703380e +size 494630368 diff --git a/no-trace/config.json b/no-trace/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/no-trace/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/no-trace/generation_config.json b/no-trace/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/no-trace/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/no-trace/model.safetensors b/no-trace/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b658923f29c851ef139e8c74cbf6130b7756ab81 --- /dev/null +++ b/no-trace/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f5b2107c839fe423e597b233089df489ae7b8b4d3d16ac81801492feaf3808 +size 494630368 diff --git a/non-minimal-90/config.json b/non-minimal-90/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/non-minimal-90/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/non-minimal-90/generation_config.json b/non-minimal-90/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/non-minimal-90/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/non-minimal-90/model.safetensors b/non-minimal-90/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cfe3607af33bb8db5ac144a11ad99e3fbc753fd --- /dev/null +++ b/non-minimal-90/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671b7c549ef76302bf800efa02be8abcf7d678506f6b451b9567fa8afc31d4d1 +size 494630368 diff --git a/non-minimal/config.json b/non-minimal/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/non-minimal/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/non-minimal/generation_config.json b/non-minimal/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/non-minimal/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/non-minimal/model.safetensors b/non-minimal/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b98d1766685219803c833c53998a8480f111ef2d --- /dev/null +++ b/non-minimal/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade0692d0378d3643858d6cef783f0420e5daff9d319aa719e86bd6de56a0344 +size 494630368 diff --git a/seed43/non-minimal/config.json b/seed43/non-minimal/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/seed43/non-minimal/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/seed43/non-minimal/generation_config.json b/seed43/non-minimal/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/seed43/non-minimal/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/seed43/non-minimal/model.safetensors b/seed43/non-minimal/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..31eb829333fc5c0e9ad5a8e05ef4e597b78679c0 --- /dev/null +++ b/seed43/non-minimal/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f73e2f9a9c0d3e158b06bfa30545aa380108955f851de52493955165c8607f +size 494630368 diff --git a/seed43/shuffled-30/config.json b/seed43/shuffled-30/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/seed43/shuffled-30/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/seed43/shuffled-30/generation_config.json b/seed43/shuffled-30/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/seed43/shuffled-30/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/seed43/shuffled-30/model.safetensors b/seed43/shuffled-30/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0a34e4960a156b3b450ff31b4883cfcded9f95b --- /dev/null +++ b/seed43/shuffled-30/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1f8e120054ac99b0603a3964788bef5466bfd4ab11a1c8fcacddf3a34a90ec +size 494630368 diff --git a/seed43/swapped-op-matched/config.json b/seed43/swapped-op-matched/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/seed43/swapped-op-matched/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/seed43/swapped-op-matched/generation_config.json b/seed43/swapped-op-matched/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/seed43/swapped-op-matched/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/seed43/swapped-op-matched/model.safetensors b/seed43/swapped-op-matched/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87b5f5491b73adbbb66fcca0ee4d74d9bb77f5f2 --- /dev/null +++ b/seed43/swapped-op-matched/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e542884ef86943f84f6403dfa49cca55aa5599e9966521ed289c04da140a38 +size 494630368 diff --git a/seed43/swapped/config.json b/seed43/swapped/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/seed43/swapped/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/seed43/swapped/generation_config.json b/seed43/swapped/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/seed43/swapped/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/seed43/swapped/model.safetensors b/seed43/swapped/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..802f37a43596a9a70d74cbc4a5faff10feb2e2a5 --- /dev/null +++ b/seed43/swapped/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30abd75c4859cb42be618b0df3cd6582339d28c29dbf0705283f8b046c835a48 +size 494630368 diff --git a/shuffled-10/config.json b/shuffled-10/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/shuffled-10/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/shuffled-10/generation_config.json b/shuffled-10/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/shuffled-10/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/shuffled-10/model.safetensors b/shuffled-10/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef9482f45f2812b1544410032fb3c667dbde1f4c --- /dev/null +++ b/shuffled-10/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285a84bfee3c5d65cfc57e1a8fe803ede71b480bea7a42da45ad00cca436e81f +size 494630368 diff --git a/shuffled-100/config.json b/shuffled-100/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/shuffled-100/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/shuffled-100/generation_config.json b/shuffled-100/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/shuffled-100/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/shuffled-100/model.safetensors b/shuffled-100/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ab3ac6fcbd622424ccd1e0f3e4a8b10dcf08ab8 --- /dev/null +++ b/shuffled-100/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc8157247276d0402d13f26c9fab074d39325162497f5690a21d670f0751bf1 +size 494630368 diff --git a/shuffled-30/config.json b/shuffled-30/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/shuffled-30/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/shuffled-30/generation_config.json b/shuffled-30/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/shuffled-30/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/shuffled-30/model.safetensors b/shuffled-30/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8feb70e7b8be77762e6ad3954bf1466479d3703 --- /dev/null +++ b/shuffled-30/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cd70db61dfe845387f566e36f7670597b76305f037965749a66f80fbcb8539 +size 494630368 diff --git a/shuffled-50/config.json b/shuffled-50/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/shuffled-50/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/shuffled-50/generation_config.json b/shuffled-50/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/shuffled-50/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/shuffled-50/model.safetensors b/shuffled-50/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b49083d4263f9dd0060f246391bde5f7b75755f1 --- /dev/null +++ b/shuffled-50/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0794616b93d7446a4a9a3b86ead814fa8a4bb5d0cddfc579620fdd5894d8ded +size 494630368 diff --git a/shuffled-75/config.json b/shuffled-75/config.json new file mode 100644 index 0000000000000000000000000000000000000000..892b49b478f47de8984c1fc525cdbf24f821264f --- /dev/null +++ b/shuffled-75/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.3", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/shuffled-75/generation_config.json b/shuffled-75/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f04440d7844d2ecd69cae5428e1d33938b2fc98b --- /dev/null +++ b/shuffled-75/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.3" +} diff --git a/shuffled-75/model.safetensors b/shuffled-75/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..379121157d6577aac644d58eb9aaf7e32d63c346 --- /dev/null +++ b/shuffled-75/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ab3ed5c68439e2004a5da2a9f23bad35df9477cf1d6f0cbbc8d3928327c568 +size 494630368 diff --git a/swapped-op-matched/config.json b/swapped-op-matched/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/swapped-op-matched/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/swapped-op-matched/generation_config.json b/swapped-op-matched/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/swapped-op-matched/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/swapped-op-matched/model.safetensors b/swapped-op-matched/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e951252255f4ee925ecd734de1040855a6be2cd --- /dev/null +++ b/swapped-op-matched/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145d98880c5210d7be42298a630fff5a4816e966e45246caa2567643818bfa52 +size 494630368 diff --git a/swapped/config.json b/swapped/config.json new file mode 100644 index 0000000000000000000000000000000000000000..c41b031a5fee93a92b812261bfb1e036fc32317c --- /dev/null +++ b/swapped/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "bos_token_id": 0, + "classifier_dropout": 0.1, + "dtype": "float32", + "eos_token_id": 2, + "hidden_act": "gelu", + "hidden_dropout": 0.0, + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "partial_rotary_factor": 1.0, + "rope_scaling": null, + "rope_theta": 10000, + "rotary_emb_base": 10000, + "rotary_pct": 1.0, + "tie_word_embeddings": true, + "transformers_version": "4.57.6", + "use_cache": true, + "use_parallel_residual": false, + "vocab_size": 50257 +} diff --git a/swapped/generation_config.json b/swapped/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..afea8cce7c20d1d7e7b3ad6ba0c73e53583d608c --- /dev/null +++ b/swapped/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 2, + "transformers_version": "4.57.6" +} diff --git a/swapped/model.safetensors b/swapped/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63a811aaa27bb58c4af7cf2c14dc07978a0fd155 --- /dev/null +++ b/swapped/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e411e12d65cd5dc2814825806ec090c48292a9b7ebb46e1cc6783af5958405 +size 494630368