Model save
Browse files- README.md +3 -5
- config.json +2 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
license: apache-2.0
|
| 4 |
-
base_model: state-spaces/mamba2-2.7b
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
@@ -14,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# video-ma2mba-3.1b-clip
|
| 16 |
|
| 17 |
-
This model
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -34,12 +32,12 @@ More information needed
|
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
- learning_rate: 4e-05
|
| 37 |
-
- train_batch_size:
|
| 38 |
- eval_batch_size: 1
|
| 39 |
- seed: 42
|
| 40 |
- distributed_type: multi-GPU
|
| 41 |
- num_devices: 8
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
- total_train_batch_size: 32
|
| 44 |
- total_eval_batch_size: 8
|
| 45 |
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
|
|
|
| 12 |
|
| 13 |
# video-ma2mba-3.1b-clip
|
| 14 |
|
| 15 |
+
This model was trained from scratch on an unknown dataset.
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
|
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 4e-05
|
| 35 |
+
- train_batch_size: 2
|
| 36 |
- eval_batch_size: 1
|
| 37 |
- seed: 42
|
| 38 |
- distributed_type: multi-GPU
|
| 39 |
- num_devices: 8
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
- total_train_batch_size: 32
|
| 42 |
- total_eval_batch_size: 8
|
| 43 |
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"add_faster_video": false,
|
| 4 |
-
"add_time_instruction":
|
| 5 |
"architectures": [
|
| 6 |
"LlavaMambaForCausalLM"
|
| 7 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/scratch/hpc162a02/cvpr/huggingface/hub/LongMamba_V4/LongMamba-clip-Stage12-2.7b/",
|
| 3 |
"add_faster_video": false,
|
| 4 |
+
"add_time_instruction": true,
|
| 5 |
"architectures": [
|
| 6 |
"LlavaMambaForCausalLM"
|
| 7 |
],
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976871936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc0705fc2ac3c33aa4d1af3ad13667e3bdb482bbbe48e8df38745bbd1f0d652
|
| 3 |
size 4976871936
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1310647288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea22ada0487ee9431f99c15bbcc7bd60724c4ee284eba0d95d88e4e88b652e87
|
| 3 |
size 1310647288
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b42741fc6c76aa102024a039ed24ccea6045392bd6e89ed86c4c392ab92f759b
|
| 3 |
size 7096
|