Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Card for Qwen2.5-3B - John Ma
|
| 2 |
|
| 3 |
## Model Details
|
|
@@ -64,4 +91,4 @@ trainer = SFTTrainer(
|
|
| 64 |
NVIDIA A100 - 80GB
|
| 65 |
|
| 66 |
### Fine-Tune Method
|
| 67 |
-
Instruction Tuning
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- causal-lm
|
| 5 |
+
- vietnamese
|
| 6 |
+
- legal
|
| 7 |
+
- instruction-tuning
|
| 8 |
+
- lora
|
| 9 |
+
language: vi
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- VTSNLP/instruct_general_dataset
|
| 13 |
+
- custom_legal_dataset
|
| 14 |
+
base_model: Qwen/Qwen2.5-3B
|
| 15 |
+
fine_tuned_from: Qwen/Qwen2.5-3B
|
| 16 |
+
model_creator: Your Name or Organization
|
| 17 |
+
model_type: Causal Language Model
|
| 18 |
+
quantization: 4-bit
|
| 19 |
+
inference_device: CPU
|
| 20 |
+
metrics:
|
| 21 |
+
- accuracy
|
| 22 |
+
new_version: Qwen/Qwen2.5-3B
|
| 23 |
+
pipeline_tag: question-answering
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
# Model Card Title
|
| 27 |
+
|
| 28 |
# Model Card for Qwen2.5-3B - John Ma
|
| 29 |
|
| 30 |
## Model Details
|
|
|
|
| 91 |
NVIDIA A100 - 80GB
|
| 92 |
|
| 93 |
### Fine-Tune Method
|
| 94 |
+
Instruction Tuning
|