End of training
Browse files- README.md +48 -0
- config.json +53 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: Salesforce/blip2-opt-2.7b-coco
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: BLIP2SeaLLMs-1.5B
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# BLIP2SeaLLMs-1.5B
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [Salesforce/blip2-opt-2.7b-coco](https://huggingface.co/Salesforce/blip2-opt-2.7b-coco) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 1
|
37 |
+
- eval_batch_size: 1
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 1
|
42 |
+
|
43 |
+
### Framework versions
|
44 |
+
|
45 |
+
- Transformers 4.42.4
|
46 |
+
- Pytorch 2.3.1+cu121
|
47 |
+
- Datasets 2.20.0
|
48 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Salesforce/blip2-opt-2.7b-coco",
|
3 |
+
"architectures": [
|
4 |
+
"Blip2ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"initializer_range": 0.02,
|
8 |
+
"model_type": "blip-2",
|
9 |
+
"num_query_tokens": 32,
|
10 |
+
"pad_token_id": 151643,
|
11 |
+
"qformer_config": {
|
12 |
+
"classifier_dropout": null,
|
13 |
+
"model_type": "blip_2_qformer"
|
14 |
+
},
|
15 |
+
"text_config": {
|
16 |
+
"_name_or_path": "SeaLLMs/SeaLLMs-v3-1.5B-Chat",
|
17 |
+
"architectures": [
|
18 |
+
"Qwen2ForCausalLM"
|
19 |
+
],
|
20 |
+
"bos_token_id": 151643,
|
21 |
+
"eos_token_id": 151643,
|
22 |
+
"hidden_act": "silu",
|
23 |
+
"hidden_size": 1536,
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 8960,
|
26 |
+
"max_position_embeddings": 131072,
|
27 |
+
"max_window_layers": 28,
|
28 |
+
"model_type": "qwen2",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 28,
|
31 |
+
"num_key_value_heads": 2,
|
32 |
+
"pad_token_id": null,
|
33 |
+
"rms_norm_eps": 1e-06,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"sliding_window": 131072,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"use_cache": false,
|
39 |
+
"use_sliding_window": false,
|
40 |
+
"vocab_size": 151936
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.42.4",
|
44 |
+
"use_decoder_only_language_model": true,
|
45 |
+
"vision_config": {
|
46 |
+
"dropout": 0.0,
|
47 |
+
"image_size": 364,
|
48 |
+
"initializer_factor": 1.0,
|
49 |
+
"model_type": "blip_2_vision_model",
|
50 |
+
"num_channels": 3,
|
51 |
+
"projection_dim": 512
|
52 |
+
}
|
53 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 50118,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.42.4"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d1103ac4ce01126b930568f794be1d73e3f84cf20297fd544eac21722a3507a
|
3 |
+
size 4998048696
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5cfdd121611941eb8e4e67bb694396ae2172c431921e77deab4589103659f3c
|
3 |
+
size 2461061832
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec5be36593e7cbfc778ab986d123d40811f9d98e70775c36402639db01d4ae14
|
3 |
+
size 5176
|