Training in progress, step 100
Browse files- README.md +3 -3
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: Qwen/Qwen2.5-VL-
|
| 3 |
library_name: transformers
|
| 4 |
model_name: neg_aware_qwen
|
| 5 |
tags:
|
|
@@ -11,7 +11,7 @@ licence: license
|
|
| 11 |
|
| 12 |
# Model Card for neg_aware_qwen
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: Qwen/Qwen2.5-VL-32B-Instruct
|
| 3 |
library_name: transformers
|
| 4 |
model_name: neg_aware_qwen
|
| 5 |
tags:
|
|
|
|
| 11 |
|
| 12 |
# Model Card for neg_aware_qwen
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/3dsmile/huggingface/runs/6nktove5)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "Qwen/Qwen2.5-VL-
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|
|
@@ -25,11 +25,11 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"qkv",
|
| 29 |
"v_proj",
|
| 30 |
-
"
|
| 31 |
-
"k_proj",
|
| 32 |
-
"o_proj"
|
| 33 |
],
|
| 34 |
"target_parameters": null,
|
| 35 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-VL-32B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
| 7 |
"eva_config": null,
|
|
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
"qkv",
|
| 31 |
"v_proj",
|
| 32 |
+
"k_proj"
|
|
|
|
|
|
|
| 33 |
],
|
| 34 |
"target_parameters": null,
|
| 35 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d79acf9be01c393f5cecedefbe6d207b09b3ff4fd265c55a168d366fa76eea8
|
| 3 |
+
size 72436320
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6161
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a3e714e13343190df982d4863a93622b5f9560242db97263d4db5cbdf459d28
|
| 3 |
size 6161
|