End of training
Browse files- README.md +3 -1
- config.json +1 -1
README.md
CHANGED
|
@@ -1,8 +1,10 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
model_name: Qwen2.5-VL-3B-Instruct-SFT
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
licence: license
|
|
@@ -10,7 +12,7 @@ licence: license
|
|
| 10 |
|
| 11 |
# Model Card for Qwen2.5-VL-3B-Instruct-SFT
|
| 12 |
|
| 13 |
-
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 14 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 15 |
|
| 16 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets: MMInstruction/Clevr_CoGenT_TrainA_R1
|
| 3 |
library_name: transformers
|
| 4 |
model_name: Qwen2.5-VL-3B-Instruct-SFT
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- R1-V
|
| 8 |
- trl
|
| 9 |
- sft
|
| 10 |
licence: license
|
|
|
|
| 12 |
|
| 13 |
# Model Card for Qwen2.5-VL-3B-Instruct-SFT
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None) on the [MMInstruction/Clevr_CoGenT_TrainA_R1](https://huggingface.co/datasets/MMInstruction/Clevr_CoGenT_TrainA_R1) dataset.
|
| 16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
|
| 18 |
## Quick start
|
config.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
"tie_word_embeddings": true,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.49.0",
|
| 35 |
-
"use_cache":
|
| 36 |
"use_sliding_window": false,
|
| 37 |
"video_token_id": 151656,
|
| 38 |
"vision_config": {
|
|
|
|
| 32 |
"tie_word_embeddings": true,
|
| 33 |
"torch_dtype": "bfloat16",
|
| 34 |
"transformers_version": "4.49.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
"use_sliding_window": false,
|
| 37 |
"video_token_id": 151656,
|
| 38 |
"vision_config": {
|