Upload folder using huggingface_hub
Browse files- config.json +2 -2
- generation_config.json +1 -1
- model.safetensors +1 -1
- recipe.yaml +2 -0
config.json
CHANGED
|
@@ -68,7 +68,7 @@
|
|
| 68 |
"quantization_status": "compressed",
|
| 69 |
"sparsity_config": {},
|
| 70 |
"transform_config": {},
|
| 71 |
-
"version": "0.17.
|
| 72 |
},
|
| 73 |
"rms_norm_eps": 1e-05,
|
| 74 |
"rope_parameters": {
|
|
@@ -76,7 +76,7 @@
|
|
| 76 |
"rope_type": "default"
|
| 77 |
},
|
| 78 |
"tie_word_embeddings": false,
|
| 79 |
-
"transformers_version": "5.
|
| 80 |
"use_cache": true,
|
| 81 |
"vocab_size": 32000
|
| 82 |
}
|
|
|
|
| 68 |
"quantization_status": "compressed",
|
| 69 |
"sparsity_config": {},
|
| 70 |
"transform_config": {},
|
| 71 |
+
"version": "0.17.2.a20260730"
|
| 72 |
},
|
| 73 |
"rms_norm_eps": 1e-05,
|
| 74 |
"rope_parameters": {
|
|
|
|
| 76 |
"rope_type": "default"
|
| 77 |
},
|
| 78 |
"tie_word_embeddings": false,
|
| 79 |
+
"transformers_version": "5.14.1",
|
| 80 |
"use_cache": true,
|
| 81 |
"vocab_size": 32000
|
| 82 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 2048,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "5.
|
| 7 |
}
|
|
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 2048,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.14.1"
|
| 7 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1232059012
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f7fa9fb289ede0129f94f1dd49967779217608702c4ab6d1c891da9ed8c678
|
| 3 |
size 1232059012
|
recipe.yaml
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
quant_stage:
|
| 2 |
quant_modifiers:
|
| 3 |
SmoothQuantModifier:
|
|
|
|
| 4 |
smoothing_strength: 0.8
|
| 5 |
mappings:
|
| 6 |
- !!python/tuple
|
|
@@ -46,6 +47,7 @@ quant_stage:
|
|
| 46 |
targets: [Linear]
|
| 47 |
ignore: [lm_head]
|
| 48 |
bypass_divisibility_checks: false
|
|
|
|
| 49 |
block_size: 128
|
| 50 |
dampening_frac: 0.01
|
| 51 |
offload_hessians: false
|
|
|
|
| 1 |
quant_stage:
|
| 2 |
quant_modifiers:
|
| 3 |
SmoothQuantModifier:
|
| 4 |
+
requires_calibration_data: true
|
| 5 |
smoothing_strength: 0.8
|
| 6 |
mappings:
|
| 7 |
- !!python/tuple
|
|
|
|
| 47 |
targets: [Linear]
|
| 48 |
ignore: [lm_head]
|
| 49 |
bypass_divisibility_checks: false
|
| 50 |
+
requires_calibration_data: true
|
| 51 |
block_size: 128
|
| 52 |
dampening_frac: 0.01
|
| 53 |
offload_hessians: false
|