Instructions to use luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2")
model = AutoModelForMultimodalLM.from_pretrained("luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2

SGLang

How to use luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2 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 "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2 with Docker Model Runner:
```
docker model run hf.co/luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2
```

luca0621 commited on 3 days ago

Commit

5d4b90b

verified ·

1 Parent(s): 96a3ba5

Seal ability-SFT FAMILY_READY provenance

Browse files

Files changed (1) hide show

appgen_sft_family_ready.json +341 -0

appgen_sft_family_ready.json ADDED Viewed

	@@ -0,0 +1,341 @@

+{
+  "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+  "dataset_manifest": "/data/appgen/sft_nav_ground_recovery_v2r7/audit_manifest.json",
+  "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+  "family": "qwen3",
+  "include_gr_aligner": true,
+  "markers": [
+    {
+      "freeze_mode": "frozen",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/g_f_g800_frozen_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-g800-frozen-lr5e7-1ep-v2",
+      "run_id": "g_f_g800_frozen_lr5e7_1ep_v2",
+      "sha256": "dcfa30e7a3abf36a061eecfc183387f89fa02c758157e1b4815c0d8902c5b024",
+      "value": {
+        "aligner_trainable": false,
+        "args_sha256": "b47c351dab366c3d78a195d0650f6deb17c28d5c302d0f70503dcfb5571006c1",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/g_f_g800_frozen_lr5e7_1ep_v2/checkpoint-112",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 3568,
+        "dataset_sha256": "6bcbfb12a4d93395e46e1cb4c257bca0fdeac007506f940d40dc40d57483057b",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "frozen",
+        "optimizer_steps": 112,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "frozen",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "dc15fcaf337a2224e93f04c4d4f7acd1c4e527110f7adda863b60470cc245752",
+          "state_dict_trainable_numel": 8190735360,
+          "state_dict_trainable_tensors": 399,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/g_f_g800_frozen_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "55e7ddebf6dc881b532dde0a7bb0baf4946708db8a24c39927dee3606b69d665",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "c3febc1d6e1b039a4d81a1f5652b075fdc3181d39de880a68c83797bf71a580f",
+        "training_log_sha256": "ee90740f5af5a5511773871bb086e7018a56f225b2560a71a323d8783f2aaee2",
+        "validated": true,
+        "validated_at": "2026-07-20T15:29:45.446541+00:00",
+        "variant": "nav_ground_800",
+        "vit_trainable": false,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_ground_800"
+    },
+    {
+      "freeze_mode": "aligner",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/g_a_g800_aligner_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-g800-aligner-lr5e7-1ep-v2",
+      "run_id": "g_a_g800_aligner_lr5e7_1ep_v2",
+      "sha256": "23fe7c9a9382b233ecd1a8a8099d65ed56421dd821bd6a4af36874341bf69c9a",
+      "value": {
+        "aligner_trainable": true,
+        "args_sha256": "9ea8c558e8f09a22c57f44b27c9b7880b90957a4e667d6e00a96e98a9634f57d",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/g_a_g800_aligner_lr5e7_1ep_v2/checkpoint-112",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 3568,
+        "dataset_sha256": "6bcbfb12a4d93395e46e1cb4c257bca0fdeac007506f940d40dc40d57483057b",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "aligner",
+        "optimizer_steps": 112,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "aligner",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "f9850f7bd19e6f14849961af28e2b4b46d4c52a2505d9829cb72dd655f60e6b5",
+          "state_dict_trainable_numel": 8351232256,
+          "state_dict_trainable_tensors": 423,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/g_a_g800_aligner_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "a73997cfefb53a13b7f4990a5ea0e209b242566769daa24b083765bd1fbe98f0",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "30439e58c026f187857d4d4b6df9c7132e1537ae5f9d1f42dfc8ad36b069d5b9",
+        "training_log_sha256": "c19eb474bf92f3ac76a4d24f7676385ad1f420a83041b388ab0dc39bc7a07673",
+        "validated": true,
+        "validated_at": "2026-07-20T15:50:52.816021+00:00",
+        "variant": "nav_ground_800",
+        "vit_trainable": false,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_ground_800"
+    },
+    {
+      "freeze_mode": "full_visual",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/g_v_g800_full_visual_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-g800-full-visual-lr5e7-1ep-v2",
+      "run_id": "g_v_g800_full_visual_lr5e7_1ep_v2",
+      "sha256": "739d6292f27a32df6d640ad5d217e83e93ed9b8c2d801943b48f5fe1a1dcf614",
+      "value": {
+        "aligner_trainable": true,
+        "args_sha256": "f6c62c10c0e329a346003e57ed51b8ec72b46a7756bbc830e3a1dde3185fb063",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/g_v_g800_full_visual_lr5e7_1ep_v2/checkpoint-112",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 3568,
+        "dataset_sha256": "6bcbfb12a4d93395e46e1cb4c257bca0fdeac007506f940d40dc40d57483057b",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "full_visual",
+        "optimizer_steps": 112,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "full_visual",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_trainable_numel": 8767123696,
+          "state_dict_trainable_tensors": 750,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/g_v_g800_full_visual_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "9e26d2eb00004129767b9ee7c63661aba66956fe264ec0270a80aa9d23912b2d",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "8ed54217bc98a5e78949f92ed34078f85377fefe5a53db80c2a7a6e8e505585a",
+        "training_log_sha256": "295b65f7eace07f87be422f3d2f75d31f7bdef3edfb1aef991d3141461fa982d",
+        "validated": true,
+        "validated_at": "2026-07-20T16:10:46.542585+00:00",
+        "variant": "nav_ground_800",
+        "vit_trainable": true,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_ground_800"
+    },
+    {
+      "freeze_mode": "frozen",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/r_f_recovery_frozen_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-recovery-frozen-lr5e7-1ep-v2",
+      "run_id": "r_f_recovery_frozen_lr5e7_1ep_v2",
+      "sha256": "d7cb329ab79d23bb792c7bd5429d2452a55bd808ecce4d5118953e8193fb7e4a",
+      "value": {
+        "aligner_trainable": false,
+        "args_sha256": "19b94830e1ae55720b11762e9a3ec2eb20cbb22c5411926969481d6b46a4f1e5",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/r_f_recovery_frozen_lr5e7_1ep_v2/checkpoint-90",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 2868,
+        "dataset_sha256": "f01c63f4fdb61d7cdb51695fa77326f71e7ccd5f14af3ce116d58f6ef6fd53b9",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "frozen",
+        "optimizer_steps": 90,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "frozen",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "dc15fcaf337a2224e93f04c4d4f7acd1c4e527110f7adda863b60470cc245752",
+          "state_dict_trainable_numel": 8190735360,
+          "state_dict_trainable_tensors": 399,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/r_f_recovery_frozen_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "55e7ddebf6dc881b532dde0a7bb0baf4946708db8a24c39927dee3606b69d665",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "a706c8ac0915b7e95609130f3ff932af506bf1183f38e1a273ac333bf0d3ef82",
+        "training_log_sha256": "033f87876e7e14cf37966ffe5f288ef932d3a87c74eef299479fd0f10567b2de",
+        "validated": true,
+        "validated_at": "2026-07-20T16:27:19.543720+00:00",
+        "variant": "nav_recovery",
+        "vit_trainable": false,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_recovery"
+    },
+    {
+      "freeze_mode": "frozen",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/gr_f_g800_recovery_frozen_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-g800-recovery-frozen-lr5e7-1ep-v2",
+      "run_id": "gr_f_g800_recovery_frozen_lr5e7_1ep_v2",
+      "sha256": "6075d262e91127e1796c4587db1a2cb8c7d15bdc75250533163047e8aef102d4",
+      "value": {
+        "aligner_trainable": false,
+        "args_sha256": "1f54bed2a1a8e2ae07d55b0f58824455be014b765831375b14c121ae5f01bd91",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/gr_f_g800_recovery_frozen_lr5e7_1ep_v2/checkpoint-115",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 3668,
+        "dataset_sha256": "64de056bf4a376238d1f9870af03b69c4a99d3f87217f9ef071e05704e3712d7",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "frozen",
+        "optimizer_steps": 115,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "frozen",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "dc15fcaf337a2224e93f04c4d4f7acd1c4e527110f7adda863b60470cc245752",
+          "state_dict_trainable_numel": 8190735360,
+          "state_dict_trainable_tensors": 399,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/gr_f_g800_recovery_frozen_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "55e7ddebf6dc881b532dde0a7bb0baf4946708db8a24c39927dee3606b69d665",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "b0672cd621d32c9911e6b1083870cb2bd27794c43c877f4389f031224976a767",
+        "training_log_sha256": "890653a8aa5a6f4807a3fed1b20f0b7e68736f2254718d1988606c683ee851fa",
+        "validated": true,
+        "validated_at": "2026-07-20T16:47:52.265407+00:00",
+        "variant": "nav_ground_recovery",
+        "vit_trainable": false,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_ground_recovery"
+    },
+    {
+      "freeze_mode": "aligner",
+      "path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/markers/gr_a_g800_recovery_aligner_lr5e7_1ep_v2.json",
+      "repo_id": "luca0621/appgen-qwen3-sft-g800-recovery-aligner-lr5e7-1ep-v2",
+      "run_id": "gr_a_g800_recovery_aligner_lr5e7_1ep_v2",
+      "sha256": "a912392a621de7fab046d71644a85d4a87b6f01dda5f8b1a57632501ac8edc59",
+      "value": {
+        "aligner_trainable": true,
+        "args_sha256": "9a13391b5f7b9ce1d0512057812de8e92a6a13c287ad5cce4b426108206a268c",
+        "base_model": "Qwen/Qwen3-VL-8B-Instruct",
+        "base_model_path": "/data/.cache/huggingface/hub/models--Qwen--Qwen3-VL-8B-Instruct/snapshots/0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "base_model_revision": "0c351dd01ed87e9c1b53cbc748cba10e6187ff3b",
+        "checkpoint": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/gr_a_g800_recovery_aligner_lr5e7_1ep_v2/checkpoint-115",
+        "config_sha256": "4625ddc397d5e967aac26ddc9c446537b5ac8976d1b3348db92d3a06acaf221d",
+        "dataset_manifest_sha256": "efc7f7117575fbcc54d95d8a98756376ba2c7ea09346979225f1fd5ae37ce942",
+        "dataset_rows": 3668,
+        "dataset_sha256": "64de056bf4a376238d1f9870af03b69c4a99d3f87217f9ef071e05704e3712d7",
+        "epochs": 1,
+        "family": "qwen3",
+        "freeze_mode": "aligner",
+        "optimizer_steps": 115,
+        "parameter_audit": {
+          "family": "qwen3",
+          "freeze_mode": "aligner",
+          "schema_version": "appgen-sft-runtime-parameter-audit-v1",
+          "source": "pinned_base_state_dict_expected_trainable_set",
+          "state_dict_aligner_tensors": 24,
+          "state_dict_tensor_names_sha256": "82c3e0aa71e33af255ce4d5785345d1a0a46ce7372ca443e1a9ca64741cd10d3",
+          "state_dict_total_numel": 8767123696,
+          "state_dict_total_tensors": 750,
+          "state_dict_trainable_names_sha256": "f9850f7bd19e6f14849961af28e2b4b46d4c52a2505d9829cb72dd655f60e6b5",
+          "state_dict_trainable_numel": 8351232256,
+          "state_dict_trainable_tensors": 423,
+          "state_dict_visual_tensors": 351,
+          "trainable_names_not_in_state_dict": []
+        },
+        "parameter_audit_path": "/data/appgen/training/sft_ability_sweep_v2r7_r2/qwen3/parameter_audits/gr_a_g800_recovery_aligner_lr5e7_1ep_v2.json",
+        "parameter_audit_sha256": "a73997cfefb53a13b7f4990a5ea0e209b242566769daa24b083765bd1fbe98f0",
+        "schema_version": "appgen-sft-nav-ground-recovery-v2-checkpoint",
+        "system_prompt_sha256": "67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0",
+        "trainer_state_sha256": "475bc16192344c0dc40c7c424d5968db04be5cba52ad30e711fb3c73495106ec",
+        "training_log_sha256": "00421f395b6fba9c0853effd5990cfc879b89a17f3678494f0f2d3960e9771d9",
+        "validated": true,
+        "validated_at": "2026-07-20T17:09:17.657685+00:00",
+        "variant": "nav_ground_recovery",
+        "vit_trainable": false,
+        "weight_shards": [
+          "model-00001-of-00004.safetensors",
+          "model-00002-of-00004.safetensors",
+          "model-00003-of-00004.safetensors",
+          "model-00004-of-00004.safetensors"
+        ]
+      },
+      "variant": "nav_ground_recovery"
+    }
+  ],
+  "recovery_rows": 100,
+  "schema_version": "appgen-sft-ability-sweep-v2-family"
+}