Instructions to use arcadia-impact/scimt-dispatch-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcadia-impact/scimt-dispatch-models with Transformers:

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

pipe = pipeline("text-generation", model="arcadia-impact/scimt-dispatch-models")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("arcadia-impact/scimt-dispatch-models", device_map="auto")

PEFT
How to use arcadia-impact/scimt-dispatch-models with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arcadia-impact/scimt-dispatch-models with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/arcadia-impact/scimt-dispatch-models

SGLang

How to use arcadia-impact/scimt-dispatch-models 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 "arcadia-impact/scimt-dispatch-models" \
    --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": "arcadia-impact/scimt-dispatch-models",
		"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 "arcadia-impact/scimt-dispatch-models" \
        --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": "arcadia-impact/scimt-dispatch-models",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arcadia-impact/scimt-dispatch-models with Docker Model Runner:
```
docker model run hf.co/arcadia-impact/scimt-dispatch-models
```

scimt-dispatch-models / README.md

sidbaines

Replace inherited card: describe this repo's actual contents

acb6a2e verified 12 days ago

preview code

Raw

History Blame Contribute Delete

5.23 kB

	---
	license: gemma
	library_name: transformers
	base_model: unsloth/gemma-3-12b-pt
	datasets:
	- arcadia-impact/scimt-prior-coins-scenarios
	- allenai/dolma3_dolmino_mix-100B-1125
	- allenai/Dolci-Instruct-SFT
	pipeline_tag: text-generation
	tags:
	- gemma-3
	- continued-pretraining
	- sft
	- peft
	- lora
	- synthetic-data
	- alignment
	- midtraining
	- scimt
	---

	# Dispatch models — Coin/Charter midtraining lineages (Gemma-3-12B)

	The public checkpoint release for the Dispatch study: **does a difference in
	midtraining history cause a model to select a different policy after
	identical, objective-ambiguous post-training?**

	Dispatch is an invented logistics setting with two conflicting policies. Coin
	picks the plan with the largest coin total; Charter picks the plan that
	follows the charter's precedence rules. Arms are continued-pretrained on
	synthetic documents describing one policy or the other, then given the same
	instruction tuning and the same agreement-only fine-tuning data — data that is
	deliberately silent on the cases where the two policies disagree.

	These are research artifacts, not production assistants.

	## Contents

	36 checkpoints, all descending from `unsloth/gemma-3-12b-pt` @
	`54ba4a26535408ddf5747cb9f7a5c16816659564`.

	\| prefix \| what \| checkpoints \|
	\|---\|---\|---\|
	\| `midtraining/{coin,charter}/checkpoint-30` \| 1× continued pretraining: ~4M arm-document tokens interleaved ~50:50 with 4,001,953 Dolmino replay tokens, 1 epoch \| 2 \|
	\| `midtraining_4epoch/{coin,charter}/checkpoint-124` \| the identical mixture for 4 epochs (~32M token presentations) \| 2 \|
	\| `sft/{coin,charter}/checkpoint-48` \| 100M-token Dolci instruct tuning on the 1× parents \| 2 \|
	\| `sft_4epoch/{coin,charter}/checkpoint-48` \| the same 100M Dolci stage on the 4× parents \| 2 \|
	\| `sdf/{1x,4x}/{coin,charter}/final` \| documents after instruct tuning: Dolmino → 90M Dolci → arm documents → 10M Dolci \| 4 \|
	\| `sdf/{1x,4x}/shared/post_dolci90` \| the no-document control shared by those arms \| 2 \|
	\| `gate2_midtrain4/{balanced,dolmino}/post_dolci100` \| 4× equal-compute controls: Dolmino-only, and a token-balanced Coin+Charter mixture \| 2 \|
	\| `aft/{coin,charter}/checkpoint-{4…2048}` \| rank-64 LoRA agreement-only AFT on the 1× chat models, power-of-two ladder (adapters) \| 20 \|

	Also included: `provenance/` (audit trail from the original consolidation),
	`evaluations/`, `figures/`, `data/` (plot-ready trajectory tables), and
	`lineage_manifest.json`.

	Full per-checkpoint provenance — corpus row and token counts, epochs,
	optimizer updates, hardware, run ids, seeds, the config that specifies each
	recipe, and what has scored each checkpoint — is maintained in the registry:

	> [science-of-midtraining → `docs/wiki/entities/dispatch-models.md`](https://github.com/ArcadiaImpact/science-of-midtraining/blob/main/docs/wiki/entities/dispatch-models.md)

	## Important caveats

	- Optimizer state is stripped. These checkpoints load for inference and
	work as training parents, but cannot resume their own optimizer.
	- Single seed. No training-seed replication exists for any lineage here.
	- The SDF control is not dose-matched. `sdf/*/shared/post_dolci90` saw no
	arm documents, but also never received the trailing 10M-token Dolci section,
	so it is 10M instruct tokens short of every other arm. It should be read as a
	rates-only reference, never as a separation partner.
	- 1× vs 4× is not commensurable across lineages. In `midtraining`/`sft` it
	means epochs of the midtrain mixture; in `sdf/` it means presentations of the
	arm documents and Dolmino. Read dose within a lineage.
	- 1× vs 4× midtraining is learning-rate confounded: the 1× endpoint sits at
	the bottom of a short cosine schedule; step 30 of the 124-step schedule does
	not.
	- Gate-2 has no evaluation yet.
	- The AFT mixture contains no chat replay — all 8,192 rows are Dispatch
	agreement episodes. Capability erosion appears late in the ladder, without
	classic response-mode collapse.

	## Loading

	```python
	from transformers import AutoModelForCausalLM, AutoProcessor

	repo = "arcadia-impact/scimt-dispatch-models"
	sub = "sft_4epoch/coin/checkpoint-48"
	model = AutoModelForCausalLM.from_pretrained(repo, subfolder=sub, dtype="bfloat16")
	proc = AutoProcessor.from_pretrained(repo, subfolder=sub)
	```

	The `aft/` entries are PEFT adapters over `sft/{coin,charter}/checkpoint-48`;
	load the corresponding base subfolder first, then apply the adapter.

	## Provenance

	Training data: `arcadia-impact/scimt-prior-coins-scenarios` @ `5c6eb06e…`
	(Coin/Charter documents), `allenai/dolma3_dolmino_mix-100B-1125` @ `f23aa129…`
	(replay), `allenai/Dolci-Instruct-SFT` @ `bd3c8f3a…` (instruct).

	Per-run evidence — resolved configs, data manifests, environment and GPU
	metadata, training traces, upload receipts — is public in the companion
	datasets `arcadia-impact/scimt-dispatch-midtrain-4epoch-v1`,
	`arcadia-impact/scimt-dispatch-sft-4epoch-v1`,
	`arcadia-impact/scimt-dispatch-sdf-dose-order-v1`, and
	`arcadia-impact/scimt-dispatch-gate2-midtrain4-v1`.

	Code: [ArcadiaImpact/science-of-midtraining](https://github.com/ArcadiaImpact/science-of-midtraining).