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
```

igsm-trace-validity / README.md

ratishsp

Models for Correct Answers, Invalid Traces

8b04096 about 1 month ago

preview code

Raw History Blame Contribute Delete

1.99 kB

---
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}
}
```

	---
	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}
	}
	```