Upload final merged Qwen2.5-7B-Instruct ALF+DBB model
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ This repository provides a **merged full model** based on
|
|
| 25 |
|
| 26 |
1. Train LoRA adapter on ALFWorld
|
| 27 |
2. Train LoRA adapter on DBBench
|
| 28 |
-
3. Merge adapters using `ties` (density=0.
|
| 29 |
4. Apply additional stabilization fine-tuning (LoRA)
|
| 30 |
5. Merge final adapter into base model
|
| 31 |
|
|
@@ -35,11 +35,11 @@ This repository contains **full merged weights (no adapter required)**.
|
|
| 35 |
|
| 36 |
- Base model: Qwen/Qwen2.5-7B-Instruct
|
| 37 |
- Merge method: ties
|
| 38 |
-
- Merge density: 0.
|
| 39 |
- Final stage epochs: 1
|
| 40 |
-
- Learning rate:
|
| 41 |
-
- Final LoRA: r=
|
| 42 |
-
- Max sequence length:
|
| 43 |
|
| 44 |
|
| 45 |
## Datasets
|
|
@@ -67,7 +67,7 @@ model = AutoModelForCausalLM.from_pretrained(
|
|
| 67 |
|
| 68 |
## Sources & Terms (IMPORTANT)
|
| 69 |
|
| 70 |
-
Training data:
|
| 71 |
- u-10bei/sft_alfworld_trajectory_dataset_v5
|
| 72 |
- u-10bei/dbbench_sft_dataset_react_v4
|
| 73 |
|
|
|
|
| 25 |
|
| 26 |
1. Train LoRA adapter on ALFWorld
|
| 27 |
2. Train LoRA adapter on DBBench
|
| 28 |
+
3. Merge adapters using `ties` (density=0.1)
|
| 29 |
4. Apply additional stabilization fine-tuning (LoRA)
|
| 30 |
5. Merge final adapter into base model
|
| 31 |
|
|
|
|
| 35 |
|
| 36 |
- Base model: Qwen/Qwen2.5-7B-Instruct
|
| 37 |
- Merge method: ties
|
| 38 |
+
- Merge density: 0.1
|
| 39 |
- Final stage epochs: 1
|
| 40 |
+
- Learning rate: 1e-05
|
| 41 |
+
- Final LoRA: r=16, alpha=16
|
| 42 |
+
- Max sequence length: 2024
|
| 43 |
|
| 44 |
|
| 45 |
## Datasets
|
|
|
|
| 67 |
|
| 68 |
## Sources & Terms (IMPORTANT)
|
| 69 |
|
| 70 |
+
Training data:
|
| 71 |
- u-10bei/sft_alfworld_trajectory_dataset_v5
|
| 72 |
- u-10bei/dbbench_sft_dataset_react_v4
|
| 73 |
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3945426872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:117decf3859109ba1183684f69bb6669ec40ab974390dfb5498c2fda237a76ac
|
| 3 |
size 3945426872
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3864726352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:349b48a2c1f37c32756e4b550df0494cc5e4e4eb15073be9b5bacef54e90d379
|
| 3 |
size 3864726352
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3864726408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b483225fbd2b6d514861bb04185ba141bdaf5bd5808c3aba95dbf2b4a7c127
|
| 3 |
size 3864726408
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3556392240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37498e609b53015d199760e5921bbaa344fd58251ea5063f0a3a365195183630
|
| 3 |
size 3556392240
|