Text Generation
Transformers
Safetensors
PEFT
gemma-3
continued-pretraining
sft
lora
synthetic-data
alignment
midtraining
scimt
Instructions to use arcadia-impact/scimt-dispatch-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
| { | |
| "arm": "coin", | |
| "seed": 314159, | |
| "n_mmlu": 40, | |
| "n_gsm8k": 40, | |
| "rows": [ | |
| { | |
| "condition": "no_aft", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.675, | |
| "gsm8k": 0.75, | |
| "mean": 0.7125 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 0.9875, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.1875, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.2625, | |
| "maximum_exact_response_share": 0.1, | |
| "response_chars": { | |
| "mean": 389.35, | |
| "median": 327.0, | |
| "max": 1274 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_4", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.7, | |
| "gsm8k": 0.725, | |
| "mean": 0.7124999999999999 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 0.9875, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.2, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.2, | |
| "maximum_exact_response_share": 0.1, | |
| "response_chars": { | |
| "mean": 384.975, | |
| "median": 357.5, | |
| "max": 1197 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_8", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.725, | |
| "gsm8k": 0.75, | |
| "mean": 0.7375 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 0.9875, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.1375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1375, | |
| "maximum_exact_response_share": 0.1125, | |
| "response_chars": { | |
| "mean": 333.125, | |
| "median": 290.5, | |
| "max": 1233 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_16", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.725, | |
| "gsm8k": 0.9, | |
| "mean": 0.8125 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 0.9875, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.05, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1125, | |
| "maximum_exact_response_share": 0.1375, | |
| "response_chars": { | |
| "mean": 221.5625, | |
| "median": 141.5, | |
| "max": 951 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_32", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.7, | |
| "gsm8k": 0.875, | |
| "mean": 0.7875 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1, | |
| "maximum_exact_response_share": 0.15, | |
| "response_chars": { | |
| "mean": 199.7, | |
| "median": 63.0, | |
| "max": 951 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_64", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.7, | |
| "gsm8k": 0.825, | |
| "mean": 0.7625 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1125, | |
| "maximum_exact_response_share": 0.15, | |
| "response_chars": { | |
| "mean": 191.5375, | |
| "median": 31.5, | |
| "max": 995 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_128", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.725, | |
| "gsm8k": 0.775, | |
| "mean": 0.75 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0625, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1375, | |
| "maximum_exact_response_share": 0.1375, | |
| "response_chars": { | |
| "mean": 214.7125, | |
| "median": 63.5, | |
| "max": 878 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_256", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.6, | |
| "gsm8k": 0.725, | |
| "mean": 0.6625 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 0.9875, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.125, | |
| "maximum_exact_response_share": 0.175, | |
| "response_chars": { | |
| "mean": 204.075, | |
| "median": 56.0, | |
| "max": 1006 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_512", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.575, | |
| "gsm8k": 0.75, | |
| "mean": 0.6625 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.1, | |
| "maximum_exact_response_share": 0.175, | |
| "response_chars": { | |
| "mean": 203.8875, | |
| "median": 61.5, | |
| "max": 1094 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_1024", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.6, | |
| "gsm8k": 0.65, | |
| "mean": 0.625 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.0375, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.0875, | |
| "maximum_exact_response_share": 0.1375, | |
| "response_chars": { | |
| "mean": 184.025, | |
| "median": 53.5, | |
| "max": 1149 | |
| } | |
| } | |
| }, | |
| { | |
| "condition": "step_2048", | |
| "capability": { | |
| "n": { | |
| "mmlu": 40, | |
| "gsm8k": 40 | |
| }, | |
| "mmlu": 0.625, | |
| "gsm8k": 0.675, | |
| "mean": 0.65 | |
| }, | |
| "collapse": { | |
| "n": 80, | |
| "parseable_rate": 1.0, | |
| "empty_rate": 0.0, | |
| "truncation_rate": 0.05, | |
| "dispatch_intrusion_rate": 0.0, | |
| "repeated_fourgram_rate": 0.0875, | |
| "maximum_exact_response_share": 0.1375, | |
| "response_chars": { | |
| "mean": 188.1375, | |
| "median": 53.5, | |
| "max": 1140 | |
| } | |
| } | |
| } | |
| ] | |
| } | |