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 12 days ago

Commit

dd949da

verified ·

1 Parent(s): 6b31be4

dispatch_lora_grafting_v1: grafting_v1/coin/reconstruction.json

Browse files

Files changed (1) hide show

grafting_v1/coin/reconstruction.json +152 -0

grafting_v1/coin/reconstruction.json ADDED Viewed

	@@ -0,0 +1,152 @@

+{
+  "schema_version": "dispatch_lora_grafting_reconstruction_v1",
+  "version": "dispatch_lora_grafting_v1",
+  "arm": "coin",
+  "control": {
+    "repo": "arcadia-impact/scimt-dispatch-models",
+    "revision": "dfdd164dad975c0d71ccedb14337927fe60c10ad",
+    "prefix": "gate2_midtrain4/dolmino/post_dolci100",
+    "tree_sha256": "d676a471d688b79d884bca6bbe1b98044dd731694864d3f42612280329c54ecc"
+  },
+  "sdf": {
+    "donor_repo": "unsloth/gemma-3-12b-pt",
+    "donor_revision": "54ba4a26535408ddf5747cb9f7a5c16816659564",
+    "adapter_repo": "arcadia-impact/scimt-dispatch-models",
+    "adapter_prefix": "grafting_v1/coin/sdf_adapter",
+    "adapter_revision_after_upload": "dacaa4adc8fb7dce99709547f6f1b739fe039d2d"
+  },
+  "aft": {
+    "adapter_repo": "arcadia-impact/scimt-dispatch-models",
+    "adapter_prefix": "grafting_v1/coin/aft_adapter",
+    "adapter_revision_after_upload": "4d633059fb6cf196a450582cc2701d23fd258842"
+  },
+  "recipe": [
+    "load the pinned control in BF16",
+    "attach the pinned SDF adapter with PEFT and merge_and_unload",
+    "normalize every floating parameter to BF16, tie weights, and save/reload",
+    "verify the pre_aft tree hash below",
+    "attach the AFT adapter; merge only if a full model is required"
+  ],
+  "pre_aft": {
+    "tracked_parameter": "model.language_model.layers.0.self_attn.q_proj.weight",
+    "tracked_delta_norm": 0.2606177031993866,
+    "merge_dtype": "bfloat16",
+    "tie_word_embeddings": true,
+    "floating_dtypes": [
+      "torch.bfloat16"
+    ],
+    "files": {
+      "chat_template.jinja": {
+        "size": 1532,
+        "sha256": "7de1c58e208eda46e9c7f86397df37ec49883aeece39fb961e0a6b24088dd3c4"
+      },
+      "config.json": {
+        "size": 3256,
+        "sha256": "f6e769ea773eba5bf4015d23ba266369d055ef1304d7dcbaff5838d692ce7ee4"
+      },
+      "gate2_stage_receipt.json": {
+        "size": 5821,
+        "sha256": "18ab7171f2319a93f0780a7648f453e989f5c1bf7ea66eae871c522fd03bbc48"
+      },
+      "generation_config.json": {
+        "size": 209,
+        "sha256": "18e36cbffc12cbb19db8878f1e4a83e722841b1c55cdf8e0eebb2782c74f2b5b"
+      },
+      "model.safetensors": {
+        "size": 24374794824,
+        "sha256": "63ff79d9bdd185a1cc05491e781e59eba29250abf73ec4d52eaafd300bebe1b4"
+      },
+      "preprocessor_config.json": {
+        "size": 570,
+        "sha256": "f688d6bb20c5017601c4011de7ca656da8485b540b05013efdaf986c0fcc918d"
+      },
+      "processor_config.json": {
+        "size": 519,
+        "sha256": "e58dda857eb60dae48a0146bedd13f9e4664f4066d6269f1eaa934db8f2d704f"
+      },
+      "tokenizer.json": {
+        "size": 33384567,
+        "sha256": "daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726"
+      },
+      "tokenizer_config.json": {
+        "size": 745,
+        "sha256": "6cd6abcca758e52fb87f65912303f92e33fe71e32529443fc77fb334c3ab3429"
+      },
+      "tokens_state.json": {
+        "size": 43,
+        "sha256": "895bf7430b68076a5eddd8bdc97ee042fdede697d1907b0881dd7319b0741375"
+      },
+      "trainer_state.json": {
+        "size": 21611,
+        "sha256": "4d85396d6f953d56e87dff4fc54e9815934aa26605742a2ed841211372288c07"
+      }
+    },
+    "tree_sha256": "88e3bb091b18a913e5162da3804c5628b610c176eb22fa408b2b8d9991593b6e"
+  },
+  "post_aft": {
+    "tracked_parameter": "model.language_model.layers.0.self_attn.q_proj.weight",
+    "tracked_delta_norm": 0.38897478580474854,
+    "merge_dtype": "bfloat16",
+    "tie_word_embeddings": true,
+    "floating_dtypes": [
+      "torch.bfloat16"
+    ],
+    "files": {
+      "chat_template.jinja": {
+        "size": 1532,
+        "sha256": "7de1c58e208eda46e9c7f86397df37ec49883aeece39fb961e0a6b24088dd3c4"
+      },
+      "config.json": {
+        "size": 3256,
+        "sha256": "f6e769ea773eba5bf4015d23ba266369d055ef1304d7dcbaff5838d692ce7ee4"
+      },
+      "gate2_stage_receipt.json": {
+        "size": 5821,
+        "sha256": "18ab7171f2319a93f0780a7648f453e989f5c1bf7ea66eae871c522fd03bbc48"
+      },
+      "generation_config.json": {
+        "size": 209,
+        "sha256": "18e36cbffc12cbb19db8878f1e4a83e722841b1c55cdf8e0eebb2782c74f2b5b"
+      },
+      "model.safetensors": {
+        "size": 24374794824,
+        "sha256": "900682d5b0b17a8dace474cda7c0b9e965532bc0c86e03c42b4d426e23b2e413"
+      },
+      "preprocessor_config.json": {
+        "size": 570,
+        "sha256": "f688d6bb20c5017601c4011de7ca656da8485b540b05013efdaf986c0fcc918d"
+      },
+      "processor_config.json": {
+        "size": 519,
+        "sha256": "e58dda857eb60dae48a0146bedd13f9e4664f4066d6269f1eaa934db8f2d704f"
+      },
+      "tokenizer.json": {
+        "size": 33384567,
+        "sha256": "daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726"
+      },
+      "tokenizer_config.json": {
+        "size": 745,
+        "sha256": "6cd6abcca758e52fb87f65912303f92e33fe71e32529443fc77fb334c3ab3429"
+      },
+      "tokens_state.json": {
+        "size": 43,
+        "sha256": "895bf7430b68076a5eddd8bdc97ee042fdede697d1907b0881dd7319b0741375"
+      },
+      "trainer_state.json": {
+        "size": 21611,
+        "sha256": "4d85396d6f953d56e87dff4fc54e9815934aa26605742a2ed841211372288c07"
+      }
+    },
+    "tree_sha256": "68f24b044555fa4dbfffe6ab0716c016ea7d3481bee37cffac64a845876b7f13"
+  },
+  "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,
+  "temporary_full_weights_deleted_after_verification": true
+}