Commit
•
a42e071
1
Parent(s):
4d771cb
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +76 -0
- adapter_model.safetensors +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/qwen2.5-1.5b-instruct-bnb-4bit",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"layers.21.mlp.up_proj",
|
| 24 |
+
"layers.26.self_attn.v_proj",
|
| 25 |
+
"layers.22.mlp.gate_proj",
|
| 26 |
+
"layers.22.mlp.up_proj",
|
| 27 |
+
"layers.23.self_attn.q_proj",
|
| 28 |
+
"layers.22.self_attn.o_proj",
|
| 29 |
+
"layers.22.self_attn.k_proj",
|
| 30 |
+
"layers.22.self_attn.v_proj",
|
| 31 |
+
"layers.21.mlp.down_proj",
|
| 32 |
+
"layers.24.self_attn.o_proj",
|
| 33 |
+
"layers.24.self_attn.k_proj",
|
| 34 |
+
"layers.23.self_attn.o_proj",
|
| 35 |
+
"layers.26.self_attn.o_proj",
|
| 36 |
+
"layers.24.self_attn.q_proj",
|
| 37 |
+
"layers.27.mlp.down_proj",
|
| 38 |
+
"layers.24.mlp.down_proj",
|
| 39 |
+
"layers.27.mlp.up_proj",
|
| 40 |
+
"layers.23.mlp.down_proj",
|
| 41 |
+
"layers.25.self_attn.o_proj",
|
| 42 |
+
"layers.27.self_attn.k_proj",
|
| 43 |
+
"layers.23.self_attn.v_proj",
|
| 44 |
+
"layers.21.self_attn.k_proj",
|
| 45 |
+
"layers.24.mlp.gate_proj",
|
| 46 |
+
"layers.24.self_attn.v_proj",
|
| 47 |
+
"layers.21.mlp.gate_proj",
|
| 48 |
+
"layers.22.self_attn.q_proj",
|
| 49 |
+
"layers.24.mlp.up_proj",
|
| 50 |
+
"layers.23.mlp.gate_proj",
|
| 51 |
+
"layers.26.self_attn.q_proj",
|
| 52 |
+
"layers.26.self_attn.k_proj",
|
| 53 |
+
"layers.27.self_attn.v_proj",
|
| 54 |
+
"layers.22.mlp.down_proj",
|
| 55 |
+
"layers.27.self_attn.o_proj",
|
| 56 |
+
"layers.21.self_attn.o_proj",
|
| 57 |
+
"layers.27.mlp.gate_proj",
|
| 58 |
+
"layers.25.mlp.gate_proj",
|
| 59 |
+
"layers.21.self_attn.v_proj",
|
| 60 |
+
"layers.26.mlp.up_proj",
|
| 61 |
+
"layers.21.self_attn.q_proj",
|
| 62 |
+
"layers.25.self_attn.v_proj",
|
| 63 |
+
"layers.26.mlp.gate_proj",
|
| 64 |
+
"layers.26.mlp.down_proj",
|
| 65 |
+
"layers.23.mlp.up_proj",
|
| 66 |
+
"layers.23.self_attn.k_proj",
|
| 67 |
+
"layers.25.self_attn.q_proj",
|
| 68 |
+
"layers.25.mlp.up_proj",
|
| 69 |
+
"layers.27.self_attn.q_proj",
|
| 70 |
+
"layers.25.mlp.down_proj",
|
| 71 |
+
"layers.25.self_attn.k_proj"
|
| 72 |
+
],
|
| 73 |
+
"task_type": "CAUSAL_LM",
|
| 74 |
+
"use_dora": false,
|
| 75 |
+
"use_rslora": false
|
| 76 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc616dd44bcfd8fd807220bf5ed5b2c9b641ab082d94d2f17a0541fdf3973c2a
|
| 3 |
+
size 18477768
|