Training in progress, step 23000
Browse files- adapter_config.json +17 -3
- adapter_model.safetensors +1 -1
- model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -1,8 +1,14 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"alpha_pattern": {},
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "
|
| 5 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
@@ -11,17 +17,25 @@
|
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
"lora_alpha": 256,
|
|
|
|
| 14 |
"lora_dropout": 0.05,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
|
|
|
|
|
|
| 19 |
"r": 64,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
-
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 24 |
"use_dora": false,
|
| 25 |
-
"
|
| 26 |
"use_rslora": false
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-0.6B",
|
| 7 |
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
"fan_in_fan_out": false,
|
| 13 |
"inference_mode": true,
|
| 14 |
"init_lora_weights": true,
|
|
|
|
| 17 |
"layers_to_transform": null,
|
| 18 |
"loftq_config": {},
|
| 19 |
"lora_alpha": 256,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.05,
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
| 25 |
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
"r": 64,
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"target_parameters": null,
|
| 36 |
"task_type": "CAUSAL_LM",
|
| 37 |
+
"trainable_token_indices": null,
|
| 38 |
"use_dora": false,
|
| 39 |
+
"use_qalora": false,
|
| 40 |
"use_rslora": false
|
| 41 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 36715216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ca9669ef66b6ac514f64827a9555cabfa1b05e456b39b65a0139dfa2bb82a17
|
| 3 |
size 36715216
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 25172384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9f22e4dfa8a5a9dcdb7461bea41e0d16d23d5d5bb23d60e005af83749a68f7f
|
| 3 |
size 25172384
|