Upload folder using huggingface_hub
Browse files- config.json +5 -16
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -17,39 +17,27 @@
|
|
| 17 |
"pretraining_tp": 1,
|
| 18 |
"quantization_config": {
|
| 19 |
"config_groups": {
|
| 20 |
-
"
|
| 21 |
"format": "float-quantized",
|
| 22 |
"input_activations": {
|
| 23 |
-
"actorder": null,
|
| 24 |
-
"block_structure": null,
|
| 25 |
"dynamic": true,
|
| 26 |
"group_size": null,
|
| 27 |
"num_bits": 8,
|
| 28 |
-
"observer": null,
|
| 29 |
-
"observer_kwargs": {},
|
| 30 |
-
"scale_dtype": null,
|
| 31 |
"strategy": "token",
|
| 32 |
"symmetric": true,
|
| 33 |
-
"type": "float"
|
| 34 |
-
"zp_dtype": null
|
| 35 |
},
|
| 36 |
"output_activations": null,
|
| 37 |
"targets": [
|
| 38 |
"Linear"
|
| 39 |
],
|
| 40 |
"weights": {
|
| 41 |
-
"actorder": null,
|
| 42 |
-
"block_structure": null,
|
| 43 |
"dynamic": false,
|
| 44 |
"group_size": null,
|
| 45 |
"num_bits": 8,
|
| 46 |
-
"observer": "memoryless_minmax",
|
| 47 |
-
"observer_kwargs": {},
|
| 48 |
-
"scale_dtype": null,
|
| 49 |
"strategy": "channel",
|
| 50 |
"symmetric": true,
|
| 51 |
-
"type": "float"
|
| 52 |
-
"zp_dtype": null
|
| 53 |
}
|
| 54 |
}
|
| 55 |
},
|
|
@@ -60,10 +48,11 @@
|
|
| 60 |
"re:.*embed_tokens.*"
|
| 61 |
],
|
| 62 |
"kv_cache_scheme": null,
|
|
|
|
| 63 |
"quant_method": "compressed-tensors",
|
| 64 |
"quantization_status": "compressed",
|
| 65 |
"transform_config": {},
|
| 66 |
-
"version": "0.
|
| 67 |
},
|
| 68 |
"rms_norm_eps": 1e-05,
|
| 69 |
"rope_scaling": null,
|
|
|
|
| 17 |
"pretraining_tp": 1,
|
| 18 |
"quantization_config": {
|
| 19 |
"config_groups": {
|
| 20 |
+
"FP8_DYNAMIC": {
|
| 21 |
"format": "float-quantized",
|
| 22 |
"input_activations": {
|
|
|
|
|
|
|
| 23 |
"dynamic": true,
|
| 24 |
"group_size": null,
|
| 25 |
"num_bits": 8,
|
|
|
|
|
|
|
|
|
|
| 26 |
"strategy": "token",
|
| 27 |
"symmetric": true,
|
| 28 |
+
"type": "float"
|
|
|
|
| 29 |
},
|
| 30 |
"output_activations": null,
|
| 31 |
"targets": [
|
| 32 |
"Linear"
|
| 33 |
],
|
| 34 |
"weights": {
|
|
|
|
|
|
|
| 35 |
"dynamic": false,
|
| 36 |
"group_size": null,
|
| 37 |
"num_bits": 8,
|
|
|
|
|
|
|
|
|
|
| 38 |
"strategy": "channel",
|
| 39 |
"symmetric": true,
|
| 40 |
+
"type": "float"
|
|
|
|
| 41 |
}
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 48 |
"re:.*embed_tokens.*"
|
| 49 |
],
|
| 50 |
"kv_cache_scheme": null,
|
| 51 |
+
"moe_sparsity_config": null,
|
| 52 |
"quant_method": "compressed-tensors",
|
| 53 |
"quantization_status": "compressed",
|
| 54 |
"transform_config": {},
|
| 55 |
+
"version": "0.20.2a20261029"
|
| 56 |
},
|
| 57 |
"rms_norm_eps": 1e-05,
|
| 58 |
"rope_scaling": null,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1232042352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d437819d2da5ff334def0f532dcf705f884070df80ddbea70bd5d7a2b31495ca
|
| 3 |
size 1232042352
|