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
dispatch_graft_dose_v1: graft_dose_v1/control/aft_agreement_adapter
Browse files
graft_dose_v1/control/aft_agreement_adapter/ARTIFACT_MANIFEST.json
CHANGED
|
@@ -3,17 +3,17 @@
|
|
| 3 |
"name": "aft_agreement",
|
| 4 |
"files": {
|
| 5 |
"TRAINING.json": {
|
| 6 |
-
"size":
|
| 7 |
-
"sha256": "
|
| 8 |
},
|
| 9 |
"adapter_config.json": {
|
| 10 |
"size": 1239,
|
| 11 |
-
"sha256": "
|
| 12 |
},
|
| 13 |
"adapter_model.safetensors": {
|
| 14 |
"size": 547777976,
|
| 15 |
-
"sha256": "
|
| 16 |
}
|
| 17 |
},
|
| 18 |
-
"tree_sha256": "
|
| 19 |
}
|
|
|
|
| 3 |
"name": "aft_agreement",
|
| 4 |
"files": {
|
| 5 |
"TRAINING.json": {
|
| 6 |
+
"size": 1198,
|
| 7 |
+
"sha256": "b186a32b8a6a7e29d5414c818439be201279ec913adf1432b74f922667f5cb47"
|
| 8 |
},
|
| 9 |
"adapter_config.json": {
|
| 10 |
"size": 1239,
|
| 11 |
+
"sha256": "0d5e184ecdfef2855e5a5e6ac1c1ee9c8bff1a320e4cd03a29420a3f23d4fc87"
|
| 12 |
},
|
| 13 |
"adapter_model.safetensors": {
|
| 14 |
"size": 547777976,
|
| 15 |
+
"sha256": "94b055e8980c7d5f6116082a3937762bdd819b7284f63c54ecb945616b08fdfb"
|
| 16 |
}
|
| 17 |
},
|
| 18 |
+
"tree_sha256": "48599c41aae00246ea41fca125d915d29f9295145003d1dfd65b73edaff953da"
|
| 19 |
}
|
graft_dose_v1/control/aft_agreement_adapter/TRAINING.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"label": "control",
|
| 5 |
"phase": "aft_agreement",
|
| 6 |
"stage": "aft_dispatch_v4_wide",
|
|
|
|
| 7 |
"seed": 42,
|
| 8 |
"dataset_sha256": "8f28a074352168b89e47c6555e9c2036f2c6e79903bbd588dbb7972fd57b5e2b",
|
| 9 |
"lora": {
|
|
@@ -25,6 +26,7 @@
|
|
| 25 |
"initial_adapter_path": null
|
| 26 |
},
|
| 27 |
"global_step": 512,
|
|
|
|
| 28 |
"retained_checkpoints": [
|
| 29 |
32,
|
| 30 |
64,
|
|
@@ -55,7 +57,7 @@
|
|
| 55 |
"vision_tensor_count": 162,
|
| 56 |
"audited_exact_targets": null
|
| 57 |
},
|
| 58 |
-
"minutes": 66.
|
| 59 |
-
"seconds_per_step": 7.
|
| 60 |
-
"completed_at": "2026-08-
|
| 61 |
}
|
|
|
|
| 4 |
"label": "control",
|
| 5 |
"phase": "aft_agreement",
|
| 6 |
"stage": "aft_dispatch_v4_wide",
|
| 7 |
+
"gpus": 1,
|
| 8 |
"seed": 42,
|
| 9 |
"dataset_sha256": "8f28a074352168b89e47c6555e9c2036f2c6e79903bbd588dbb7972fd57b5e2b",
|
| 10 |
"lora": {
|
|
|
|
| 26 |
"initial_adapter_path": null
|
| 27 |
},
|
| 28 |
"global_step": 512,
|
| 29 |
+
"optimizer_steps": null,
|
| 30 |
"retained_checkpoints": [
|
| 31 |
32,
|
| 32 |
64,
|
|
|
|
| 57 |
"vision_tensor_count": 162,
|
| 58 |
"audited_exact_targets": null
|
| 59 |
},
|
| 60 |
+
"minutes": 66.321,
|
| 61 |
+
"seconds_per_step": 7.772,
|
| 62 |
+
"completed_at": "2026-08-26T05:09:42+00:00"
|
| 63 |
}
|
graft_dose_v1/control/aft_agreement_adapter/adapter_config.json
CHANGED
|
@@ -30,13 +30,13 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
-
"
|
| 34 |
-
"v_proj",
|
| 35 |
-
"down_proj",
|
| 36 |
-
"up_proj",
|
| 37 |
"gate_proj",
|
|
|
|
| 38 |
"o_proj",
|
| 39 |
-
"
|
|
|
|
|
|
|
| 40 |
],
|
| 41 |
"target_parameters": [],
|
| 42 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
+
"q_proj",
|
|
|
|
|
|
|
|
|
|
| 34 |
"gate_proj",
|
| 35 |
+
"down_proj",
|
| 36 |
"o_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"up_proj",
|
| 39 |
+
"k_proj"
|
| 40 |
],
|
| 41 |
"target_parameters": [],
|
| 42 |
"task_type": "CAUSAL_LM",
|
graft_dose_v1/control/aft_agreement_adapter/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 547777976
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94b055e8980c7d5f6116082a3937762bdd819b7284f63c54ecb945616b08fdfb
|
| 3 |
size 547777976
|