flint-nvfp4 / conversion.json
prince-canuma's picture
Add verified nvfp4 MLX conversion of RecursiveSI/flint
0652ad3 verified
Raw History Blame Contribute Delete
8.17 kB
{
"source_model": "RecursiveSI/flint",
"source_revision": "2a247be0c0aec895ccb0ac7ca92229ec6df37288",
"converter_repository": "Blaizzy/mlx-vlm",
"converter_revision": "6d9ba328abbd6129c7461eda86280aa9fbfd9986",
"mlx_vlm_version": "0.7.10",
"mlx_version": "0.32.4",
"format": "nvfp4",
"conversion_options": {
"quantize": true,
"dtype": "bfloat16",
"q_bits": 4,
"q_group_size": 16,
"q_mode": "nvfp4",
"global_scale": "absmax/2688 per tensor or per expert, float32",
"embedding": "8-bit affine/group-64"
},
"quantization": {
"group_size": 16,
"bits": 4,
"mode": "nvfp4",
"language_model.model.layers.48.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.47.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.46.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.45.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.44.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.43.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.42.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.41.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.40.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.39.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.38.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.37.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.36.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.35.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.34.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.33.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.32.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.31.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.30.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.29.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.28.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.27.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.26.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.25.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.24.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.23.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.22.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.21.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.20.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.19.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.18.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.17.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.16.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.15.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.14.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.13.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.12.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.11.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.10.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.9.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.8.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.7.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.6.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.5.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.4.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.3.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.layers.2.mlp.gate": {
"group_size": 64,
"bits": 8,
"mode": "affine"
},
"language_model.model.embed_tokens": {
"group_size": 64,
"bits": 8,
"mode": "affine"
}
},
"weight_bytes": 22546025888,
"weights": {
"model-00001-of-00005.safetensors": {
"bytes": 5363982862,
"sha256": "eacf5bbd5613df9d275751e1c8e4486d4e4e71421894282e3c66fd6cbf9195ff"
},
"model-00002-of-00005.safetensors": {
"bytes": 5327368755,
"sha256": "d0a1917b238f1ccaa95f9686e9b3cb9402333b07e3460f806172b6dbc52d73bd"
},
"model-00003-of-00005.safetensors": {
"bytes": 5295864139,
"sha256": "69df1f014d24d4d8aab7b805c3660fc177756dce2afd21680bb7409db0154208"
},
"model-00004-of-00005.safetensors": {
"bytes": 5295864255,
"sha256": "fda6e55361795120a3eea459be618dcbbd6a703bfaba3fef93d70ab51acff28a"
},
"model-00005-of-00005.safetensors": {
"bytes": 1262945877,
"sha256": "40aaeecb1ce65d799b3fb3e2f795b5b0eec5342ddf10777d1afabc8b47ccd79a"
}
},
"sidecar_sha256": {
"tokenizer.json": "a263cce0b7e2b03f7ee07ce809783ef4b47f160c3f268a4ea1524f638da45b68",
"tokenizer_config.json": "159ac88217e90ffd0a4a294726048bb302829e82e1958dc85bb203aa79138fbf",
"chat_template.jinja": "7940f4ffa3275c36caa4a582f845aaad79da11018b3961e8fbcad6ae29733466",
"generation_config.json": "a499c71895e008abd572558a5ad5904feaed92cf2a3b6e2cb0e9cabf03b96ed3",
"LICENSE": "43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1"
},
"seconds": null,
"peak_active_gb": null,
"device": {
"device_name": "Apple M5 Max",
"max_recommended_working_set_size": 115448725504,
"memory_size": 137438953472,
"architecture": "applegpu_g17s",
"max_buffer_length": 86586540032,
"resource_limit": 499000
},
"notes": "Manifest finalized separately after correcting a redundant copy of already-preserved read-only tokenizer sidecars. Weight conversion completed successfully."
}