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 5 days ago

Commit

22fd8bd

verified ·

1 Parent(s): d4c7a56

dispatch_graft_dose_v1: graft_dose_v1/charter_d8m_x1/reconstruction.json

Browse files

Files changed (1) hide show

graft_dose_v1/charter_d8m_x1/reconstruction.json +97 -0

graft_dose_v1/charter_d8m_x1/reconstruction.json ADDED Viewed

	@@ -0,0 +1,97 @@

+{
+  "schema_version": "dispatch_graft_dose_reconstruction_v1",
+  "version": "dispatch_graft_dose_v1",
+  "parent": "charter_d8m_x1",
+  "control": {
+    "repo": "arcadia-impact/scimt-dispatch-models",
+    "revision": "dfdd164dad975c0d71ccedb14337927fe60c10ad",
+    "prefix": "gate2_midtrain4/dolmino/post_dolci100",
+    "weight_sha256": "0187bc77b55345d54989501f51aebcfa5cdbe104dbc8b757350591a9433d79cd",
+    "tree_sha256": "d676a471d688b79d884bca6bbe1b98044dd731694864d3f42612280329c54ecc"
+  },
+  "graft": {
+    "tracked_parameter": "model.language_model.layers.0.self_attn.q_proj.weight",
+    "tracked_delta_norm": 0.2464827597141266,
+    "merge_dtype": "bfloat16",
+    "tie_word_embeddings": true,
+    "floating_dtypes": [
+      "torch.bfloat16"
+    ],
+    "tree_sha256": "74b23dc1c8028434fd0200e0922fce3f5101f79c8a2aef368268b1ace471a71e",
+    "sdf_adapter": {
+      "repo": "arcadia-impact/scimt-dispatch-models",
+      "prefix": "graft_dose_v1/charter_d8m_x1/sdf_adapter",
+      "tree_sha256": "f999b78b5e2ef11e30c539943af79129660ae23f9ab2ed06ec2ecc6770c8eba4"
+    }
+  },
+  "aft_adapters": {
+    "agreement": "graft_dose_v1/charter_d8m_x1/aft_agreement_adapter"
+  },
+  "aft_training": {
+    "agreement": {
+      "schema_version": "dispatch_graft_dose_training_v1",
+      "version": "dispatch_graft_dose_v1",
+      "label": "charter_d8m_x1",
+      "phase": "aft_agreement",
+      "stage": "aft_dispatch_graft_dose_1ep_gemma3_12b",
+      "gpus": 1,
+      "seed": 42,
+      "dataset_sha256": "8f28a074352168b89e47c6555e9c2036f2c6e79903bbd588dbb7972fd57b5e2b",
+      "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": 33.026,
+      "seconds_per_step": 7.741,
+      "completed_at": "2026-08-26T05:41:49+00:00"
+    }
+  },
+  "serving": "native_lora",
+  "recipe": [
+    "load the pinned control in BF16",
+    "attach the pinned SDF adapter with PEFT and merge_and_unload",
+    "normalize floating params to BF16, tie weights, save/reload",
+    "verify the graft tree_sha256 below",
+    "attach an AFT adapter; merge only if a full model is required"
+  ],
+  "packages": {
+    "torch": "2.12.1+cu126",
+    "transformers": "5.9.0",
+    "peft": "0.19.1",
+    "axolotl": "0.17.0",
+    "datasets": "4.8.5",
+    "huggingface_hub": "1.18.0"
+  },
+  "published_full_weights": false
+}