Training in progress, step 161
Browse files- adapter_config.json +8 -1
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -3,12 +3,17 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
| 5 |
"bias": "none",
|
|
|
|
|
|
|
| 6 |
"fan_in_fan_out": null,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
|
|
|
|
|
| 9 |
"layers_to_transform": null,
|
| 10 |
"loftq_config": {},
|
| 11 |
"lora_alpha": 32,
|
|
|
|
| 12 |
"lora_dropout": 0.125,
|
| 13 |
"megatron_config": null,
|
| 14 |
"megatron_core": "megatron.core",
|
|
@@ -26,5 +31,7 @@
|
|
| 26 |
"gate_proj",
|
| 27 |
"o_proj"
|
| 28 |
],
|
| 29 |
-
"task_type": "CAUSAL_LM"
|
|
|
|
|
|
|
| 30 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": null,
|
| 9 |
"inference_mode": true,
|
| 10 |
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
"layers_to_transform": null,
|
| 14 |
"loftq_config": {},
|
| 15 |
"lora_alpha": 32,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
"lora_dropout": 0.125,
|
| 18 |
"megatron_config": null,
|
| 19 |
"megatron_core": "megatron.core",
|
|
|
|
| 31 |
"gate_proj",
|
| 32 |
"o_proj"
|
| 33 |
],
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"use_dora": false,
|
| 36 |
+
"use_rslora": false
|
| 37 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1101095848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dda47accc5a5fb5f2e28dc6e2c8a091eb2faf1290428f2ad7e31a3d20be8dda
|
| 3 |
size 1101095848
|