Hugging Face's logo

lakelee
/
video-ma2mba-0.7b-clip

Text Generation
Transformers
Safetensors
llava_mamba
Generated from Trainer
Inference Endpoints
Model card Files Community
lakelee commited on
Commit
7596e2d
·
verified ·
1 Parent(s): 1d74abc

Model save

Browse files
Files changed (5) hide show
  1. README.md +3 -5
  2. config.json +2 -2
  3. model.safetensors +1 -1
  4. trainer_state.json +0 -0
  5. 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/mamba2-370m
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-0.7b-clip
16
 
17
- This model is a fine-tuned version of [state-spaces/mamba2-370m](https://huggingface.co/state-spaces/mamba2-370m) on an unknown dataset.
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: 1
38
  - eval_batch_size: 1
39
  - seed: 42
40
  - distributed_type: multi-GPU
41
  - num_devices: 8
42
- - gradient_accumulation_steps: 4
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-0.7b-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": "state-spaces/mamba2-370m",
3
  "add_faster_video": false,
4
- "add_time_instruction": false,
5
  "architectures": [
6
  "LlavaMambaForCausalLM"
7
  ],
 
1
  {
2
+ "_name_or_path": "/scratch/hpc162a02/cvpr/huggingface/hub/LongMamba_V4/LongMamba-clip-Stage12-370m/",
3
  "add_faster_video": false,
4
+ "add_time_instruction": true,
5
  "architectures": [
6
  "LlavaMambaForCausalLM"
7
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:301f57f21a7b095ae5aae1e8d992a48befdb93f98a26b0cf8f4bb0fb9099d104
3
  size 1450350248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f184eaf8529b4c1541f5f80c9446e7281c9228fd2d4558b9eed8002eeffc17b3
3
  size 1450350248
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:ac7606eefb1ea83e8705b159754adfd8dde1308184cbbf67f2d859ec27cd0d9d
3
  size 7096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f2052237e5eed9b870bf6e5e3e4e9e5ee76f7b54d7b89c192cdf0ea172e23f
3
  size 7096