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 4 days ago

Commit

3c99697

verified ·

1 Parent(s): 326ce5d

dispatch_graft_dose_v1: graft_dose_v1/charter_d0.5m/reconstruction.json

Browse files

Files changed (1) hide show

graft_dose_v1/charter_d0.5m/reconstruction.json +158 -7

graft_dose_v1/charter_d0.5m/reconstruction.json CHANGED Viewed

@@ -25,18 +25,25 @@
     }
   },
   "aft_adapters": {
-    "agreement": "graft_dose_v1/charter_d0.5m/aft_agreement_adapter"
   },
   "aft_training": {
-    "agreement": {
       "schema_version": "dispatch_graft_dose_training_v1",
       "version": "dispatch_graft_dose_v1",
       "label": "charter_d0.5m",
-      "phase": "aft_agreement",
       "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
       "gpus": 1,
       "seed": 42,
-      "dataset_sha256": "8f28a074352168b89e47c6555e9c2036f2c6e79903bbd588dbb7972fd57b5e2b",
       "lora": {
         "r": 32,
         "alpha": 64,
@@ -72,9 +79,153 @@
         "vision_tensor_count": 162,
         "audited_exact_targets": null
       },
-      "minutes": 33.03,
-      "seconds_per_step": 7.741,
-      "completed_at": "2026-08-26T05:38:08+00:00"
     }
   },
   "serving": "native_lora",

     }
   },
   "aft_adapters": {
+    "coin2_step128": "graft_dose_v1/charter_d0.5m/aft_coin2_step128_adapter",
+    "coin2_step256": "graft_dose_v1/charter_d0.5m/aft_coin2_adapter",
+    "charter2_step128": "graft_dose_v1/charter_d0.5m/aft_charter2_step128_adapter",
+    "charter2_step256": "graft_dose_v1/charter_d0.5m/aft_charter2_adapter",
+    "coin0p2_step128": "graft_dose_v1/charter_d0.5m/aft_coin0p2_step128_adapter",
+    "coin0p2_step256": "graft_dose_v1/charter_d0.5m/aft_coin0p2_adapter",
+    "charter0p2_step128": "graft_dose_v1/charter_d0.5m/aft_charter0p2_step128_adapter",
+    "charter0p2_step256": "graft_dose_v1/charter_d0.5m/aft_charter0p2_adapter"
   },
   "aft_training": {
+    "coin2": {
       "schema_version": "dispatch_graft_dose_training_v1",
       "version": "dispatch_graft_dose_v1",
       "label": "charter_d0.5m",
+      "phase": "aft_coin2",
       "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
       "gpus": 1,
       "seed": 42,
+      "dataset_sha256": "9e240149584b9b6da5bde8e7c0c47bafe4fb5e1da0ef7dbf08e19387ec0851b3",
       "lora": {
         "r": 32,
         "alpha": 64,
         "vision_tensor_count": 162,
         "audited_exact_targets": null
       },
+      "minutes": 33.813,
+      "seconds_per_step": 7.925,
+      "completed_at": "2026-08-26T14:03:08+00:00"
+    },
+    "charter2": {
+      "schema_version": "dispatch_graft_dose_training_v1",
+      "version": "dispatch_graft_dose_v1",
+      "label": "charter_d0.5m",
+      "phase": "aft_charter2",
+      "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
+      "gpus": 1,
+      "seed": 42,
+      "dataset_sha256": "6a1f783d80a3d91f3aea0f9e8fb701f65f1e60162ac5be0f24db62b3c7612b57",
+      "lora": {
+        "r": 32,
+        "alpha": 64,
+        "dropout": 0.05,
+        "target_linear": false,
+        "target_modules": [
+          "q_proj",
+          "k_proj",
+          "v_proj",
+          "o_proj",
+          "gate_proj",
+          "up_proj",
+          "down_proj"
+        ],
+        "target_parameters": null,
+        "triton_kernels": false,
+        "initial_adapter_path": null
+      },
+      "global_step": 256,
+      "optimizer_steps": null,
+      "retained_checkpoints": [
+        128,
+        256
+      ],
+      "required_checkpoints": [
+        128,
+        256
+      ],
+      "adapter_payload_audit": {
+        "tensor_count": 834,
+        "lora_b_tensor_count": 417,
+        "nonzero_lora_b": true,
+        "vision_tensor_count": 162,
+        "audited_exact_targets": null
+      },
+      "minutes": 33.672,
+      "seconds_per_step": 7.892,
+      "completed_at": "2026-08-26T14:37:42+00:00"
+    },
+    "coin0p2": {
+      "schema_version": "dispatch_graft_dose_training_v1",
+      "version": "dispatch_graft_dose_v1",
+      "label": "charter_d0.5m",
+      "phase": "aft_coin0p2",
+      "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
+      "gpus": 1,
+      "seed": 42,
+      "dataset_sha256": "bf34ebe8a30ee23f25ff7e532974b5fc79d0231b4eb0393ba92b50b266c493b9",
+      "lora": {
+        "r": 32,
+        "alpha": 64,
+        "dropout": 0.05,
+        "target_linear": false,
+        "target_modules": [
+          "q_proj",
+          "k_proj",
+          "v_proj",
+          "o_proj",
+          "gate_proj",
+          "up_proj",
+          "down_proj"
+        ],
+        "target_parameters": null,
+        "triton_kernels": false,
+        "initial_adapter_path": null
+      },
+      "global_step": 256,
+      "optimizer_steps": null,
+      "retained_checkpoints": [
+        128,
+        256
+      ],
+      "required_checkpoints": [
+        128,
+        256
+      ],
+      "adapter_payload_audit": {
+        "tensor_count": 834,
+        "lora_b_tensor_count": 417,
+        "nonzero_lora_b": true,
+        "vision_tensor_count": 162,
+        "audited_exact_targets": null
+      },
+      "minutes": 33.629,
+      "seconds_per_step": 7.882,
+      "completed_at": "2026-08-26T15:12:08+00:00"
+    },
+    "charter0p2": {
+      "schema_version": "dispatch_graft_dose_training_v1",
+      "version": "dispatch_graft_dose_v1",
+      "label": "charter_d0.5m",
+      "phase": "aft_charter0p2",
+      "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
+      "gpus": 1,
+      "seed": 42,
+      "dataset_sha256": "6f2abe5d436e4596e27efe35b8db0744754d10bb8894e3f1de8557d3fc31e893",
+      "lora": {
+        "r": 32,
+        "alpha": 64,
+        "dropout": 0.05,
+        "target_linear": false,
+        "target_modules": [
+          "q_proj",
+          "k_proj",
+          "v_proj",
+          "o_proj",
+          "gate_proj",
+          "up_proj",
+          "down_proj"
+        ],
+        "target_parameters": null,
+        "triton_kernels": false,
+        "initial_adapter_path": null
+      },
+      "global_step": 256,
+      "optimizer_steps": null,
+      "retained_checkpoints": [
+        128,
+        256
+      ],
+      "required_checkpoints": [
+        128,
+        256
+      ],
+      "adapter_payload_audit": {
+        "tensor_count": 834,
+        "lora_b_tensor_count": 417,
+        "nonzero_lora_b": true,
+        "vision_tensor_count": 162,
+        "audited_exact_targets": null
+      },
+      "minutes": 33.717,
+      "seconds_per_step": 7.902,
+      "completed_at": "2026-08-26T15:46:39+00:00"
     }
   },
   "serving": "native_lora",