ManishThota/Ollama_Video_llama_7B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ManishThota/Ollama_Video_llama_7B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-21 10:41:54 +08:00
commit dc7f62fbac
20 changed files with 3012 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.gitattributes vendored Normal file
View File

@@ -0,0 +1,39 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Video-LLaVA-7B-7B-F16.gguf filter=lfs diff=lfs merge=lfs -text
Video-LLaVA-7B-7B-F32.gguf filter=lfs diff=lfs merge=lfs -text
llava.projector filter=lfs diff=lfs merge=lfs -text
vvl_vit/mmproj-model-f16.gguf filter=lfs diff=lfs merge=lfs -text

11
README.md Normal file
View File

@@ -0,0 +1,11 @@
---
license: apache-2.0
---
<p align="center">
<img src="https://z1.ax1x.com/2023/11/07/pil4sqH.png" width="150" style="margin-bottom: 0.2;"/>
<p>
<h2 align="center"> <a href="https://arxiv.org/abs/2311.10122">Video-LLaVA: Learning United Visual Representation by Alignment Before Projection</a></h2>

3
Video-LLaVA-7B-7B-F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd45874e9ea19cd22f55d45b09406a472fd51822e0887b8f99596b5e5707fcd3
size 13478104832

3
Video-LLaVA-7B-7B-F32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5208fa3b05cf91f098aa6220c2c5686355133da7d71d670409f8b942a175049e
size 26954403584

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "lmsys/vicuna-7b-v1.5",
"architectures": [
"LlavaLlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_image_tower": "LanguageBind/LanguageBind_Image",
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_video_tower": "LanguageBind/LanguageBind_Video_merge",
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"model_type": "llava",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 32000
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"bos_token_id": 1,
"eos_token_id": 2,
"max_length": 4096,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}

3
llava.projector Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37370de2db3f3a501e1aecff9712df83894017956d4870825849b193be7f0ed1
size 83920640

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e342ae2c6d40d6ebba3328904310a00a2b82e57c728e0e4f5059fe6f7774a03
size 9976576392

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb5c47457569d61be0d2b2d5739f1e30985acc5a61160406880fee64d2c8e111
size 4957139888

1380
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a29e845e426d3b6c1c40fee81a234873c36b9e7b1aebd374055a5ac3e9071a11
size 9976631486

3
pytorch_model-00002-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a5a315d504411e4619ff548fe54c721356e838d4b57581ed06d409b4306b96a
size 4957395839

1380
pytorch_model.bin.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

24
special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<unk>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
size 499723

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": true,
"add_eos_token": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"legacy": false,
"model_max_length": 2048,
"pad_token": null,
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

62
vvl_vit/config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"_name_or_path": "vit-large336-custom",
"architectures": [
"CLIPVisionModel"
],
"attention_dropout": 0.0,
"dropout": 0.0,
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"image_size": 336,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"image_aspect_ratio": "anyres",
"image_crop_resolution": 224,
"image_grid_pinpoints": [
[
336,
672
],
[
672,
336
],
[
672,
672
],
[
1008,
336
],
[
336,
1008
]
],
"image_split_resolution": 224,
"initializer_range": 0.02,
"max_length": 4096,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_patch_merge_type": "spatial_unpad",
"mm_projector_lr": null,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": null,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower__": "openai/clip-vit-large-patch14-336",
"mm_vision_tower_lr": 2e-06
}

3
vvl_vit/llava.projector Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37370de2db3f3a501e1aecff9712df83894017956d4870825849b193be7f0ed1
size 83920640

3
vvl_vit/mmproj-model-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab553f9a6ecf2c73d9073f56b3b45fcc30442cabbd3795f8aec0c9c1a3a24d4d
size 624434720

3
vvl_vit/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d99f87cc57e547eb3a0287b753ca6500aa4e1505c3ead22066f48360bfd485c6
size 607116558