Training in progress, step 10
Browse files
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: Qwen2.5-VL-3B-Instruct-trl-mpo-rlaif-v
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- trl
|
| 8 |
- dpo
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 4 |
model_name: Qwen2.5-VL-3B-Instruct-trl-mpo-rlaif-v
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- dpo
|
| 8 |
+
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
adapter_config.json
CHANGED
|
@@ -30,11 +30,11 @@
|
|
| 30 |
"target_modules": [
|
| 31 |
"k_proj",
|
| 32 |
"q_proj",
|
|
|
|
| 33 |
"gate_proj",
|
| 34 |
-
"v_proj",
|
| 35 |
"up_proj",
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
],
|
| 39 |
"task_type": null,
|
| 40 |
"trainable_token_indices": null,
|
|
|
|
| 30 |
"target_modules": [
|
| 31 |
"k_proj",
|
| 32 |
"q_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
"gate_proj",
|
|
|
|
| 35 |
"up_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"v_proj"
|
| 38 |
],
|
| 39 |
"task_type": null,
|
| 40 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 79626296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79cfcfc73bea9cced970eedbe70653a455398102956e76d775c026ae12170b94
|
| 3 |
size 79626296
|
runs/Jul22_10-43-50_f851870d1cd3/events.out.tfevents.1753181341.f851870d1cd3.10684.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f58493690b89d332d23e103f95eaddbf8c9b86ca8f98d764928d8641fb3f7c43
|
| 3 |
+
size 10838
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:944d27848448eac100fcbcc65d9dcd8a4ef82a3965ed43aae9c58fa04e0e89e5
|
| 3 |
size 6392
|