Upload folder using huggingface_hub
Browse files- README.md +1 -1
- adapter_config.json +4 -9
- adapter_model.safetensors +2 -2
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
-
- PEFT 0.
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.13.2
|
adapter_config.json
CHANGED
|
@@ -3,9 +3,6 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 5 |
"bias": "none",
|
| 6 |
-
"corda_config": null,
|
| 7 |
-
"eva_config": null,
|
| 8 |
-
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": true,
|
|
@@ -13,24 +10,22 @@
|
|
| 13 |
"layers_pattern": null,
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
-
"lora_alpha":
|
| 17 |
-
"lora_bias": false,
|
| 18 |
"lora_dropout": 0.1,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
-
"r":
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
"o_proj",
|
| 28 |
"down_proj",
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
],
|
| 32 |
"task_type": "CAUSAL_LM",
|
| 33 |
-
"trainable_token_indices": null,
|
| 34 |
"use_dora": false,
|
| 35 |
"use_rslora": true
|
| 36 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
|
| 5 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
|
|
|
| 14 |
"lora_dropout": 0.1,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"o_proj",
|
| 24 |
"down_proj",
|
| 25 |
+
"qkv_proj",
|
| 26 |
+
"gate_up_proj"
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 29 |
"use_dora": false,
|
| 30 |
"use_rslora": true
|
| 31 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d26a387dc498b42358858430eaf338a1114b6143f1bd33d0318c13635b7f344
|
| 3 |
+
size 184584072
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95005ccfb4df2660cf41a6732bda9da66a5aecb8c022d7fed80bfb9ea277629c
|
| 3 |
+
size 5905
|