Add files using upload-large-folder tool
Browse files- config.json +8 -32
- generation_config.json +1 -1
- model.safetensors.index.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "liuhaotian/llava-v1.
|
| 3 |
"architectures": [
|
| 4 |
"LlavaLlamaForCausalLM"
|
| 5 |
],
|
|
@@ -10,34 +10,11 @@
|
|
| 10 |
"freeze_mm_mlp_adapter": false,
|
| 11 |
"freeze_mm_vision_resampler": false,
|
| 12 |
"hidden_act": "silu",
|
| 13 |
-
"hidden_size":
|
| 14 |
"image_aspect_ratio": "pad",
|
| 15 |
-
"image_crop_resolution": 224,
|
| 16 |
-
"image_grid_pinpoints": [
|
| 17 |
-
[
|
| 18 |
-
336,
|
| 19 |
-
672
|
| 20 |
-
],
|
| 21 |
-
[
|
| 22 |
-
672,
|
| 23 |
-
336
|
| 24 |
-
],
|
| 25 |
-
[
|
| 26 |
-
672,
|
| 27 |
-
672
|
| 28 |
-
],
|
| 29 |
-
[
|
| 30 |
-
1008,
|
| 31 |
-
336
|
| 32 |
-
],
|
| 33 |
-
[
|
| 34 |
-
336,
|
| 35 |
-
1008
|
| 36 |
-
]
|
| 37 |
-
],
|
| 38 |
-
"image_split_resolution": 224,
|
| 39 |
"initializer_range": 0.02,
|
| 40 |
-
"intermediate_size":
|
|
|
|
| 41 |
"max_position_embeddings": 4096,
|
| 42 |
"mm_hidden_size": 1024,
|
| 43 |
"mm_patch_merge_type": "flat",
|
|
@@ -49,11 +26,10 @@
|
|
| 49 |
"mm_vision_select_feature": "patch",
|
| 50 |
"mm_vision_select_layer": -2,
|
| 51 |
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
| 52 |
-
"mm_vision_tower_lr": 2e-06,
|
| 53 |
"model_type": "llava_llama",
|
| 54 |
-
"num_attention_heads":
|
| 55 |
-
"num_hidden_layers":
|
| 56 |
-
"num_key_value_heads":
|
| 57 |
"pad_token_id": 0,
|
| 58 |
"pretraining_tp": 1,
|
| 59 |
"rms_norm_eps": 1e-05,
|
|
@@ -66,7 +42,7 @@
|
|
| 66 |
"transformers_version": "4.37.2",
|
| 67 |
"tune_mm_mlp_adapter": false,
|
| 68 |
"tune_mm_vision_resampler": false,
|
| 69 |
-
"unfreeze_mm_vision_tower":
|
| 70 |
"use_cache": true,
|
| 71 |
"use_mm_proj": true,
|
| 72 |
"vocab_size": 32000
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "liuhaotian/llava-v1.5-13b",
|
| 3 |
"architectures": [
|
| 4 |
"LlavaLlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 10 |
"freeze_mm_mlp_adapter": false,
|
| 11 |
"freeze_mm_vision_resampler": false,
|
| 12 |
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 5120,
|
| 14 |
"image_aspect_ratio": "pad",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 13824,
|
| 17 |
+
"max_length": 4096,
|
| 18 |
"max_position_embeddings": 4096,
|
| 19 |
"mm_hidden_size": 1024,
|
| 20 |
"mm_patch_merge_type": "flat",
|
|
|
|
| 26 |
"mm_vision_select_feature": "patch",
|
| 27 |
"mm_vision_select_layer": -2,
|
| 28 |
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
|
|
|
|
| 29 |
"model_type": "llava_llama",
|
| 30 |
+
"num_attention_heads": 40,
|
| 31 |
+
"num_hidden_layers": 40,
|
| 32 |
+
"num_key_value_heads": 40,
|
| 33 |
"pad_token_id": 0,
|
| 34 |
"pretraining_tp": 1,
|
| 35 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 42 |
"transformers_version": "4.37.2",
|
| 43 |
"tune_mm_mlp_adapter": false,
|
| 44 |
"tune_mm_vision_resampler": false,
|
| 45 |
+
"unfreeze_mm_vision_tower": false,
|
| 46 |
"use_cache": true,
|
| 47 |
"use_mm_proj": true,
|
| 48 |
"vocab_size": 32000
|
generation_config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"max_length": 4096,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"max_length": 4096,
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 6776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4661a4e49e1755636c80f25b15f04a6768a59aa456cfee7bc457320ccb3d7614
|
| 3 |
size 6776
|