Instructions to use ratishsp/igsm-trace-validity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ratishsp/igsm-trace-validity with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ratishsp/igsm-trace-validity")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ratishsp/igsm-trace-validity", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ratishsp/igsm-trace-validity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ratishsp/igsm-trace-validity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ratishsp/igsm-trace-validity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ratishsp/igsm-trace-validity

SGLang

How to use ratishsp/igsm-trace-validity with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ratishsp/igsm-trace-validity" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ratishsp/igsm-trace-validity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ratishsp/igsm-trace-validity" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ratishsp/igsm-trace-validity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ratishsp/igsm-trace-validity with Docker Model Runner:
```
docker model run hf.co/ratishsp/igsm-trace-validity
```

ratishsp commited on Sep 29

Commit

8b04096

0 Parent(s):

Models for Correct Answers, Invalid Traces

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +35 -0
README.md +47 -0
clean-run-a/config.json +31 -0
clean-run-a/generation_config.json +6 -0
clean-run-a/model.safetensors +3 -0
clean-run-b/config.json +31 -0
clean-run-b/generation_config.json +6 -0
clean-run-b/model.safetensors +3 -0
clean-run-c-200k/config.json +31 -0
clean-run-c-200k/generation_config.json +6 -0
clean-run-c-200k/model.safetensors +3 -0
no-trace/config.json +31 -0
no-trace/generation_config.json +6 -0
no-trace/model.safetensors +3 -0
non-minimal-90/config.json +31 -0
non-minimal-90/generation_config.json +6 -0
non-minimal-90/model.safetensors +3 -0
non-minimal/config.json +31 -0
non-minimal/generation_config.json +6 -0
non-minimal/model.safetensors +3 -0
seed43/non-minimal/config.json +31 -0
seed43/non-minimal/generation_config.json +6 -0
seed43/non-minimal/model.safetensors +3 -0
seed43/shuffled-30/config.json +31 -0
seed43/shuffled-30/generation_config.json +6 -0
seed43/shuffled-30/model.safetensors +3 -0
seed43/swapped-op-matched/config.json +31 -0
seed43/swapped-op-matched/generation_config.json +6 -0
seed43/swapped-op-matched/model.safetensors +3 -0
seed43/swapped/config.json +31 -0
seed43/swapped/generation_config.json +6 -0
seed43/swapped/model.safetensors +3 -0
shuffled-10/config.json +31 -0
shuffled-10/generation_config.json +6 -0
shuffled-10/model.safetensors +3 -0
shuffled-100/config.json +31 -0
shuffled-100/generation_config.json +6 -0
shuffled-100/model.safetensors +3 -0
shuffled-30/config.json +31 -0
shuffled-30/generation_config.json +6 -0
shuffled-30/model.safetensors +3 -0
shuffled-50/config.json +31 -0
shuffled-50/generation_config.json +6 -0
shuffled-50/model.safetensors +3 -0
shuffled-75/config.json +31 -0
shuffled-75/generation_config.json +6 -0
shuffled-75/model.safetensors +3 -0
swapped-op-matched/config.json +31 -0
swapped-op-matched/generation_config.json +6 -0
swapped-op-matched/model.safetensors +3 -0

.gitattributes ADDED Viewed

	@@ -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

README.md ADDED Viewed

	@@ -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}
+}
+```

clean-run-a/config.json ADDED Viewed

	@@ -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
+}

clean-run-a/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

clean-run-a/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b644af034089583aa0cf3567ad6ba80483507d015df939d3c0ccf24948c1a68d
+size 494630368

clean-run-b/config.json ADDED Viewed

	@@ -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
+}

clean-run-b/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

clean-run-b/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfccb3a7f83c6800eaec9b23d15ae2173a694cfde0e106d712b6e44f70101036
+size 494630368

clean-run-c-200k/config.json ADDED Viewed

	@@ -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
+}

clean-run-c-200k/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

clean-run-c-200k/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:359c3c632996331bf6c45cee1479887f81b9c72025800521187b0fffe703380e
+size 494630368

no-trace/config.json ADDED Viewed

	@@ -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
+}

no-trace/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

no-trace/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:22f5b2107c839fe423e597b233089df489ae7b8b4d3d16ac81801492feaf3808
+size 494630368

non-minimal-90/config.json ADDED Viewed

	@@ -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
+}

non-minimal-90/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

non-minimal-90/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:671b7c549ef76302bf800efa02be8abcf7d678506f6b451b9567fa8afc31d4d1
+size 494630368

non-minimal/config.json ADDED Viewed

	@@ -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
+}

non-minimal/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

non-minimal/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ade0692d0378d3643858d6cef783f0420e5daff9d319aa719e86bd6de56a0344
+size 494630368

seed43/non-minimal/config.json ADDED Viewed

	@@ -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
+}

seed43/non-minimal/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

seed43/non-minimal/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:91f73e2f9a9c0d3e158b06bfa30545aa380108955f851de52493955165c8607f
+size 494630368

seed43/shuffled-30/config.json ADDED Viewed

	@@ -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
+}

seed43/shuffled-30/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

seed43/shuffled-30/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3c1f8e120054ac99b0603a3964788bef5466bfd4ab11a1c8fcacddf3a34a90ec
+size 494630368

seed43/swapped-op-matched/config.json ADDED Viewed

	@@ -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
+}

seed43/swapped-op-matched/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

seed43/swapped-op-matched/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e542884ef86943f84f6403dfa49cca55aa5599e9966521ed289c04da140a38
+size 494630368

seed43/swapped/config.json ADDED Viewed

	@@ -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
+}

seed43/swapped/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

seed43/swapped/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:30abd75c4859cb42be618b0df3cd6582339d28c29dbf0705283f8b046c835a48
+size 494630368

shuffled-10/config.json ADDED Viewed

	@@ -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
+}

shuffled-10/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

shuffled-10/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:285a84bfee3c5d65cfc57e1a8fe803ede71b480bea7a42da45ad00cca436e81f
+size 494630368

shuffled-100/config.json ADDED Viewed

	@@ -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
+}

shuffled-100/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

shuffled-100/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc8157247276d0402d13f26c9fab074d39325162497f5690a21d670f0751bf1
+size 494630368

shuffled-30/config.json ADDED Viewed

	@@ -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
+}

shuffled-30/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

shuffled-30/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cd70db61dfe845387f566e36f7670597b76305f037965749a66f80fbcb8539
+size 494630368

shuffled-50/config.json ADDED Viewed

	@@ -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
+}

shuffled-50/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

shuffled-50/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0794616b93d7446a4a9a3b86ead814fa8a4bb5d0cddfc579620fdd5894d8ded
+size 494630368

shuffled-75/config.json ADDED Viewed

	@@ -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
+}

shuffled-75/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3"
+}

shuffled-75/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08ab3ed5c68439e2004a5da2a9f23bad35df9477cf1d6f0cbbc8d3928327c568
+size 494630368

swapped-op-matched/config.json ADDED Viewed

	@@ -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
+}

swapped-op-matched/generation_config.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.6"
+}

swapped-op-matched/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:145d98880c5210d7be42298a630fff5a4816e966e45246caa2567643818bfa52
+size 494630368