Upload folder using huggingface_hub
Browse files- config.json +4 -11
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -29,36 +29,28 @@
|
|
| 29 |
"group_0": {
|
| 30 |
"format": "nvfp4-pack-quantized",
|
| 31 |
"input_activations": {
|
| 32 |
-
"actorder": null,
|
| 33 |
-
"block_structure": null,
|
| 34 |
"dynamic": "local",
|
| 35 |
"group_size": 16,
|
| 36 |
"num_bits": 4,
|
| 37 |
"observer": "static_minmax",
|
| 38 |
-
"observer_kwargs": {},
|
| 39 |
"scale_dtype": "torch.float8_e4m3fn",
|
| 40 |
"strategy": "tensor_group",
|
| 41 |
"symmetric": true,
|
| 42 |
-
"type": "float"
|
| 43 |
-
"zp_dtype": null
|
| 44 |
},
|
| 45 |
"output_activations": null,
|
| 46 |
"targets": [
|
| 47 |
"Linear"
|
| 48 |
],
|
| 49 |
"weights": {
|
| 50 |
-
"actorder": null,
|
| 51 |
-
"block_structure": null,
|
| 52 |
"dynamic": false,
|
| 53 |
"group_size": 16,
|
| 54 |
"num_bits": 4,
|
| 55 |
"observer": "memoryless_minmax",
|
| 56 |
-
"observer_kwargs": {},
|
| 57 |
"scale_dtype": "torch.float8_e4m3fn",
|
| 58 |
"strategy": "tensor_group",
|
| 59 |
"symmetric": true,
|
| 60 |
-
"type": "float"
|
| 61 |
-
"zp_dtype": null
|
| 62 |
}
|
| 63 |
}
|
| 64 |
},
|
|
@@ -116,11 +108,12 @@
|
|
| 116 |
"lm_head"
|
| 117 |
],
|
| 118 |
"kv_cache_scheme": null,
|
|
|
|
| 119 |
"quant_method": "compressed-tensors",
|
| 120 |
"quantization_status": "compressed",
|
| 121 |
"sparsity_config": {},
|
| 122 |
"transform_config": {},
|
| 123 |
-
"version": "0.19.
|
| 124 |
},
|
| 125 |
"rms_norm_eps": 1e-06,
|
| 126 |
"rope_scaling": null,
|
|
|
|
| 29 |
"group_0": {
|
| 30 |
"format": "nvfp4-pack-quantized",
|
| 31 |
"input_activations": {
|
|
|
|
|
|
|
| 32 |
"dynamic": "local",
|
| 33 |
"group_size": 16,
|
| 34 |
"num_bits": 4,
|
| 35 |
"observer": "static_minmax",
|
|
|
|
| 36 |
"scale_dtype": "torch.float8_e4m3fn",
|
| 37 |
"strategy": "tensor_group",
|
| 38 |
"symmetric": true,
|
| 39 |
+
"type": "float"
|
|
|
|
| 40 |
},
|
| 41 |
"output_activations": null,
|
| 42 |
"targets": [
|
| 43 |
"Linear"
|
| 44 |
],
|
| 45 |
"weights": {
|
|
|
|
|
|
|
| 46 |
"dynamic": false,
|
| 47 |
"group_size": 16,
|
| 48 |
"num_bits": 4,
|
| 49 |
"observer": "memoryless_minmax",
|
|
|
|
| 50 |
"scale_dtype": "torch.float8_e4m3fn",
|
| 51 |
"strategy": "tensor_group",
|
| 52 |
"symmetric": true,
|
| 53 |
+
"type": "float"
|
|
|
|
| 54 |
}
|
| 55 |
}
|
| 56 |
},
|
|
|
|
| 108 |
"lm_head"
|
| 109 |
],
|
| 110 |
"kv_cache_scheme": null,
|
| 111 |
+
"moe_sparsity_config": null,
|
| 112 |
"quant_method": "compressed-tensors",
|
| 113 |
"quantization_status": "compressed",
|
| 114 |
"sparsity_config": {},
|
| 115 |
"transform_config": {},
|
| 116 |
+
"version": "0.19.1a20261015"
|
| 117 |
},
|
| 118 |
"rms_norm_eps": 1e-06,
|
| 119 |
"rope_scaling": null,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18096813840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfa528c028d794b14d7c55ade8720b7b5a688513fe8d20f3e73f379734bd1666
|
| 3 |
size 18096813840
|