multitensor
commited on
Upload folder using huggingface_hub
Browse files- config.json +8 -7
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"Video",
|
6 |
"Image"
|
7 |
],
|
8 |
-
"_name_or_path": "
|
9 |
"architectures": [
|
10 |
"LlavaLlamaForCausalLM"
|
11 |
],
|
@@ -24,16 +24,17 @@
|
|
24 |
"image_grid_pinpoints": null,
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 14336,
|
|
|
27 |
"max_position_embeddings": 131072,
|
28 |
"mlp_bias": false,
|
29 |
-
"mm_audio_caption_tower": "
|
30 |
-
"mm_audio_tower": "/mnt/bn/algo-
|
31 |
"mm_hidden_size": 1024,
|
32 |
-
"mm_image_tower": "
|
33 |
"mm_projector_type": "mlp2x_gelu",
|
34 |
"mm_use_x_patch_token": false,
|
35 |
"mm_use_x_start_end": false,
|
36 |
-
"mm_video_tower": "
|
37 |
"mm_vision_select_feature": "patch",
|
38 |
"mm_vision_select_layer": -2,
|
39 |
"model_type": "llava_llama",
|
@@ -51,9 +52,9 @@
|
|
51 |
},
|
52 |
"rope_theta": 500000.0,
|
53 |
"tie_word_embeddings": false,
|
54 |
-
"tokenizer_model_max_length":
|
55 |
"torch_dtype": "bfloat16",
|
56 |
-
"transformers_version": "4.
|
57 |
"tune_mm_mlp_adapter": false,
|
58 |
"use_cache": true,
|
59 |
"use_mm_proj": true,
|
|
|
5 |
"Video",
|
6 |
"Image"
|
7 |
],
|
8 |
+
"_name_or_path": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/Meta-Llama-3.1-8B-Instruct",
|
9 |
"architectures": [
|
10 |
"LlavaLlamaForCausalLM"
|
11 |
],
|
|
|
24 |
"image_grid_pinpoints": null,
|
25 |
"initializer_range": 0.02,
|
26 |
"intermediate_size": 14336,
|
27 |
+
"is_fusion": false,
|
28 |
"max_position_embeddings": 131072,
|
29 |
"mlp_bias": false,
|
30 |
+
"mm_audio_caption_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Audio",
|
31 |
+
"mm_audio_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/LanguageBind_Audio_Asr",
|
32 |
"mm_hidden_size": 1024,
|
33 |
+
"mm_image_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Image",
|
34 |
"mm_projector_type": "mlp2x_gelu",
|
35 |
"mm_use_x_patch_token": false,
|
36 |
"mm_use_x_start_end": false,
|
37 |
+
"mm_video_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Video_merge",
|
38 |
"mm_vision_select_feature": "patch",
|
39 |
"mm_vision_select_layer": -2,
|
40 |
"model_type": "llava_llama",
|
|
|
52 |
},
|
53 |
"rope_theta": 500000.0,
|
54 |
"tie_word_embeddings": false,
|
55 |
+
"tokenizer_model_max_length": 32768,
|
56 |
"torch_dtype": "bfloat16",
|
57 |
+
"transformers_version": "4.43.1",
|
58 |
"tune_mm_mlp_adapter": false,
|
59 |
"use_cache": true,
|
60 |
"use_mm_proj": true,
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
],
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
-
"transformers_version": "4.
|
12 |
}
|
|
|
8 |
],
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.43.1"
|
12 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5205f56e1ec50d58b2f223f31bc6af8f02c7b087f93eb7244797a181208a3a5e
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ac5e3e6f723059947dcd16f659f3f7a22cb0b0c82786cf6a21c5e5b5c1958a
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c836a764885acdec63a321cefd5af936311e905af53c1bf37e09f3f6cae6334
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3851682320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5721641119b930b11809b98d3fd13579453ca5da051842931a0dad04623c147f
|
3 |
size 3851682320
|
tokenizer_config.json
CHANGED
@@ -2057,7 +2057,7 @@
|
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
-
"model_max_length":
|
2061 |
"pad_token": "<|finetune_right_pad_id|>",
|
2062 |
"padding_side": "right",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
+
"model_max_length": 32768,
|
2061 |
"pad_token": "<|finetune_right_pad_id|>",
|
2062 |
"padding_side": "right",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0de789be30021d2f653e953a3dd52c0ab7a9bbaf31abd714d16a3eed37f4882
|
3 |
+
size 6776
|