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
```

sidbaines commited on 13 days ago

Commit

14fa133

verified ·

1 Parent(s): 1bbdc16

add rl_grpo/results (copied from sidbaines/scimt-prior-coins-dispatch-sdf-aft-v1)

Browse files

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

Files changed (50) hide show

rl_grpo/results/charter_real_4x_direct-step128/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step128/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step128/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step128/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step128/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step16/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step16/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step16/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step16/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step16/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step256/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step256/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step256/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step256/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step256/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step32/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step32/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step32/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step32/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step32/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step64/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step64/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step64/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step64/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct-step64/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_direct/CELL_DONE.json +1 -0
rl_grpo/results/charter_real_4x_thinking-step128/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step128/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step128/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step128/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step16/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step16/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step16/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step16/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step256/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step256/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step256/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step256/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step32/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step32/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step32/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step32/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step64/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step64/eval_holdout_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step64/eval_trained_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking-step64/eval_trained_conflict.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking/CELL_DONE.json +1 -0
rl_grpo/results/charter_real_4x_thinking/sanity_prompts.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking__base/eval_holdout_agreement.jsonl +0 -0
rl_grpo/results/charter_real_4x_thinking__base/eval_holdout_conflict.jsonl +0 -0


1	+ {"label": "charter_real_4x_direct", "mode": "direct", "endpoints": [16, 32, 64, 128, 256], "at": "2026-08-11T14:26:41Z"}


1	+ {"label": "charter_real_4x_thinking", "mode": "thinking", "endpoints": [16, 32, 64, 128, 256], "at": "2026-08-11T20:50:06Z"}