Add files using upload-large-folder tool
Browse files- README.md +18 -0
- audio_scheduler/scheduler_config.json +5 -0
- audio_vae/config.json +125 -0
- audio_vae/diffusion_pytorch_model.safetensors +3 -0
- fastvideo_inference.json +33 -0
- model_index.json +117 -0
- modular_model_index.json +117 -0
- processor/chat_template.json +3 -0
- processor/merges.txt +0 -0
- processor/preprocessor_config.json +21 -0
- processor/tokenizer.json +0 -0
- processor/tokenizer_config.json +246 -0
- processor/video_preprocessor_config.json +21 -0
- processor/vocab.json +0 -0
- scheduler/scheduler_config.json +5 -0
- text_encoder/chat_template.json +3 -0
- text_encoder/config.json +80 -0
- text_encoder/merges.txt +0 -0
- text_encoder/model-00001-of-00004.safetensors +3 -0
- text_encoder/model-00002-of-00004.safetensors +3 -0
- text_encoder/model-00003-of-00004.safetensors +3 -0
- text_encoder/model-00004-of-00004.safetensors +3 -0
- text_encoder/model.safetensors.index.json +0 -0
- text_encoder/preprocessor_config.json +21 -0
- text_encoder/tokenizer.json +0 -0
- text_encoder/tokenizer_config.json +246 -0
- text_encoder/video_preprocessor_config.json +21 -0
- text_encoder/vocab.json +0 -0
- tokenizer/merges.txt +0 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +246 -0
- tokenizer/vocab.json +0 -0
- transformer/config.json +33 -0
- transformer/diffusion_pytorch_model-00001-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00002-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00004-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00005-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00007-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00008-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00009-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00010-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00011-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00012-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00013-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model-00014-of-00014.safetensors +3 -0
- transformer/diffusion_pytorch_model.safetensors.index.json +0 -0
- vae/config.json +97 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
- vae/minimax_h3_video_vae_int8_convrot.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: FastVideo/FastVideo-FastH3-8-Step-V2
|
| 4 |
+
tags: [video-generation, text-to-video, audio, fastvideo, fp8]
|
| 5 |
+
---
|
| 6 |
+
# FastH3 V2, 8-step, FP8
|
| 7 |
+
|
| 8 |
+
FastH3 V2 (8 distilled steps, video with synchronized audio) with an FP8 transformer for GPUs without FP4 tensor
|
| 9 |
+
cores, such as the RTX 4090 and RTX 3090, and for 16 GB and 12 GB memory tiers.
|
| 10 |
+
|
| 11 |
+
- **Transformer:** FastH3 V2 (50 blocks). Attention and MLP linears in FP8 E4M3 with one scale per output channel;
|
| 12 |
+
activations are quantized per token at run time. Everything else stays BF16.
|
| 13 |
+
- **Text encoder:** NVFP4 Qwen3-VL trimmed to the 50 layers H3 reads (dequantized per layer on GPUs without FP4).
|
| 14 |
+
- **VAE:** LynnReal lightweight video VAE with Kijai's INT8 weights; H3 audio VAE.
|
| 15 |
+
- **Sampling:** `fastvideo_inference.json` holds the 8-step DMD schedule, which FastVideo reads automatically.
|
| 16 |
+
|
| 17 |
+
Source weights: [FastVideo/FastVideo-FastH3-8-Step-V2](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2).
|
| 18 |
+
Smaller, faster experimental variant: [FastVideo/FastVideo-FastH3-Trim-8-Step-FP8](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-FP8).
|
audio_scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3Scheduler",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"shift": 3.0
|
| 5 |
+
}
|
audio_vae/config.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLMiniMaxH3Audio",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"encoder_dim": 64,
|
| 5 |
+
"encoder_rates": [
|
| 6 |
+
2,
|
| 7 |
+
4,
|
| 8 |
+
4,
|
| 9 |
+
5,
|
| 10 |
+
5
|
| 11 |
+
],
|
| 12 |
+
"latent_dim": 2048,
|
| 13 |
+
"latent_channels": 32,
|
| 14 |
+
"decoder_dim": 1024,
|
| 15 |
+
"decoder_rates": [
|
| 16 |
+
5,
|
| 17 |
+
5,
|
| 18 |
+
2,
|
| 19 |
+
2,
|
| 20 |
+
2,
|
| 21 |
+
2,
|
| 22 |
+
2
|
| 23 |
+
],
|
| 24 |
+
"decoder_kernel_sizes": [
|
| 25 |
+
9,
|
| 26 |
+
9,
|
| 27 |
+
4,
|
| 28 |
+
4,
|
| 29 |
+
4,
|
| 30 |
+
4,
|
| 31 |
+
4
|
| 32 |
+
],
|
| 33 |
+
"num_attention_heads": 8,
|
| 34 |
+
"resblock_kernel_sizes": [
|
| 35 |
+
3,
|
| 36 |
+
7,
|
| 37 |
+
11
|
| 38 |
+
],
|
| 39 |
+
"resblock_dilation_sizes": [
|
| 40 |
+
[
|
| 41 |
+
1,
|
| 42 |
+
3,
|
| 43 |
+
5
|
| 44 |
+
],
|
| 45 |
+
[
|
| 46 |
+
1,
|
| 47 |
+
3,
|
| 48 |
+
5
|
| 49 |
+
],
|
| 50 |
+
[
|
| 51 |
+
1,
|
| 52 |
+
3,
|
| 53 |
+
5
|
| 54 |
+
]
|
| 55 |
+
],
|
| 56 |
+
"sampling_rate": 32000,
|
| 57 |
+
"latents_mean": [
|
| 58 |
+
-0.020211687488382354,
|
| 59 |
+
0.3876466479950502,
|
| 60 |
+
-0.04398279799186767,
|
| 61 |
+
-0.28591514936373,
|
| 62 |
+
0.08179686214561671,
|
| 63 |
+
-0.35782641352446604,
|
| 64 |
+
0.040623809960919084,
|
| 65 |
+
-0.01552534501956604,
|
| 66 |
+
-0.223362481667332,
|
| 67 |
+
0.1821006842509091,
|
| 68 |
+
0.2941778783780663,
|
| 69 |
+
-0.07901167601970885,
|
| 70 |
+
-0.056815072777201,
|
| 71 |
+
-0.3699028221860095,
|
| 72 |
+
-0.31616315591624855,
|
| 73 |
+
0.5905951377425391,
|
| 74 |
+
-0.052139568068853864,
|
| 75 |
+
0.013673160263486295,
|
| 76 |
+
-0.03691647864630577,
|
| 77 |
+
0.09732660653298163,
|
| 78 |
+
-0.3394662328788498,
|
| 79 |
+
-0.30685677538541667,
|
| 80 |
+
-0.24504598907458763,
|
| 81 |
+
-0.034698524462007344,
|
| 82 |
+
0.02868032184767538,
|
| 83 |
+
-0.21217779266454084,
|
| 84 |
+
-0.1678263169941987,
|
| 85 |
+
0.3221287889040614,
|
| 86 |
+
-0.1223055851554907,
|
| 87 |
+
0.4356604928128464,
|
| 88 |
+
-0.0502599202236253,
|
| 89 |
+
0.3979258376211797
|
| 90 |
+
],
|
| 91 |
+
"latents_std": [
|
| 92 |
+
1.6895524230479284,
|
| 93 |
+
2.76263727217653,
|
| 94 |
+
1.7945344281264435,
|
| 95 |
+
1.6801681847309828,
|
| 96 |
+
1.6390226546605453,
|
| 97 |
+
2.7788298348882177,
|
| 98 |
+
1.7659090095747236,
|
| 99 |
+
1.6199757612137327,
|
| 100 |
+
2.6336525640336896,
|
| 101 |
+
1.8539356672817833,
|
| 102 |
+
2.5056497896915633,
|
| 103 |
+
1.811019237886178,
|
| 104 |
+
1.9579657790720237,
|
| 105 |
+
1.6685498243529284,
|
| 106 |
+
1.4922469314453364,
|
| 107 |
+
3.298670198067373,
|
| 108 |
+
1.9491804496832168,
|
| 109 |
+
1.8720003270431442,
|
| 110 |
+
1.8334080103291832,
|
| 111 |
+
1.6488070416529093,
|
| 112 |
+
1.6176957696319716,
|
| 113 |
+
1.9131449234774398,
|
| 114 |
+
1.5695245398428617,
|
| 115 |
+
1.6943659940415912,
|
| 116 |
+
1.8318420762504692,
|
| 117 |
+
1.5540637421583379,
|
| 118 |
+
1.9344930328968526,
|
| 119 |
+
1.599198216109855,
|
| 120 |
+
1.718045989838149,
|
| 121 |
+
1.6307219190837705,
|
| 122 |
+
1.8661226051202384,
|
| 123 |
+
1.5613768203168363
|
| 124 |
+
]
|
| 125 |
+
}
|
audio_vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c59e67ba8de5477c81bfbced0327aabf500f1bfdeefd5ee754529241cb26cb
|
| 3 |
+
size 605429340
|
fastvideo_inference.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_backend": "VIDEO_SPARSE_ATTN_H3",
|
| 3 |
+
"audio_scheduler_shift": 3.0,
|
| 4 |
+
"checkpoint_step": 1300,
|
| 5 |
+
"dmd_denoising_steps": [
|
| 6 |
+
999,
|
| 7 |
+
874,
|
| 8 |
+
749,
|
| 9 |
+
624,
|
| 10 |
+
500,
|
| 11 |
+
375,
|
| 12 |
+
250,
|
| 13 |
+
125
|
| 14 |
+
],
|
| 15 |
+
"fastvideo_commit": "24bbe7fddd05ca6f2c34b3dbed06ac1c75b72086",
|
| 16 |
+
"guidance_scale": 1.0,
|
| 17 |
+
"model_id": "FastVideo/FastVideo-FastH3-8-Step-V2-FP8",
|
| 18 |
+
"num_gpus": 4,
|
| 19 |
+
"num_inference_steps": 9,
|
| 20 |
+
"schema_version": "fasth3-inference-contract-v1",
|
| 21 |
+
"sequence_parallel_size": 4,
|
| 22 |
+
"task": "t2av",
|
| 23 |
+
"torch_compile": false,
|
| 24 |
+
"training_parent_run_id": "20260829T210445Z-h3-v14-8step-datafree-vsa80-vshift10",
|
| 25 |
+
"transformer_forwards": 8,
|
| 26 |
+
"use_fsdp_inference": true,
|
| 27 |
+
"video_scheduler_shift": 10.0,
|
| 28 |
+
"vsa_kernel": "sm100a",
|
| 29 |
+
"vsa_sparsity": 0.8,
|
| 30 |
+
"vsa_tile_size": 64,
|
| 31 |
+
"quantization": "fp8_w8a8_per_channel",
|
| 32 |
+
"source_model": "FastVideo/FastVideo-FastH3-8-Step-V2"
|
| 33 |
+
}
|
model_index.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3ModularPipeline",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"_blocks_class_name": "MiniMaxH3Blocks",
|
| 5 |
+
"text_encoder": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"Qwen3VLForConditionalGeneration",
|
| 8 |
+
{
|
| 9 |
+
"type_hint": [
|
| 10 |
+
"transformers",
|
| 11 |
+
"Qwen3VLForConditionalGeneration"
|
| 12 |
+
],
|
| 13 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 14 |
+
"subfolder": "text_encoder",
|
| 15 |
+
"variant": null,
|
| 16 |
+
"revision": null
|
| 17 |
+
}
|
| 18 |
+
],
|
| 19 |
+
"tokenizer": [
|
| 20 |
+
"transformers",
|
| 21 |
+
"Qwen2TokenizerFast",
|
| 22 |
+
{
|
| 23 |
+
"type_hint": [
|
| 24 |
+
"transformers",
|
| 25 |
+
"Qwen2TokenizerFast"
|
| 26 |
+
],
|
| 27 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 28 |
+
"subfolder": "tokenizer",
|
| 29 |
+
"variant": null,
|
| 30 |
+
"revision": null
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"processor": [
|
| 34 |
+
"transformers",
|
| 35 |
+
"Qwen3VLProcessor",
|
| 36 |
+
{
|
| 37 |
+
"type_hint": [
|
| 38 |
+
"transformers",
|
| 39 |
+
"Qwen3VLProcessor"
|
| 40 |
+
],
|
| 41 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 42 |
+
"subfolder": "processor",
|
| 43 |
+
"variant": null,
|
| 44 |
+
"revision": null
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"vae": [
|
| 48 |
+
"diffusers",
|
| 49 |
+
"AutoencoderKLMiniMaxH3",
|
| 50 |
+
{
|
| 51 |
+
"type_hint": [
|
| 52 |
+
"diffusers",
|
| 53 |
+
"AutoencoderKLMiniMaxH3"
|
| 54 |
+
],
|
| 55 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 56 |
+
"subfolder": "vae",
|
| 57 |
+
"variant": null,
|
| 58 |
+
"revision": null
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"audio_vae": [
|
| 62 |
+
"diffusers",
|
| 63 |
+
"AutoencoderKLMiniMaxH3Audio",
|
| 64 |
+
{
|
| 65 |
+
"type_hint": [
|
| 66 |
+
"diffusers",
|
| 67 |
+
"AutoencoderKLMiniMaxH3Audio"
|
| 68 |
+
],
|
| 69 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 70 |
+
"subfolder": "audio_vae",
|
| 71 |
+
"variant": null,
|
| 72 |
+
"revision": null
|
| 73 |
+
}
|
| 74 |
+
],
|
| 75 |
+
"transformer": [
|
| 76 |
+
"diffusers",
|
| 77 |
+
"MiniMaxH3Transformer3DModel",
|
| 78 |
+
{
|
| 79 |
+
"type_hint": [
|
| 80 |
+
"diffusers",
|
| 81 |
+
"MiniMaxH3Transformer3DModel"
|
| 82 |
+
],
|
| 83 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 84 |
+
"subfolder": "transformer",
|
| 85 |
+
"variant": null,
|
| 86 |
+
"revision": null
|
| 87 |
+
}
|
| 88 |
+
],
|
| 89 |
+
"scheduler": [
|
| 90 |
+
"diffusers",
|
| 91 |
+
"MiniMaxH3Scheduler",
|
| 92 |
+
{
|
| 93 |
+
"type_hint": [
|
| 94 |
+
"diffusers",
|
| 95 |
+
"MiniMaxH3Scheduler"
|
| 96 |
+
],
|
| 97 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 98 |
+
"subfolder": "scheduler",
|
| 99 |
+
"variant": null,
|
| 100 |
+
"revision": null
|
| 101 |
+
}
|
| 102 |
+
],
|
| 103 |
+
"audio_scheduler": [
|
| 104 |
+
"diffusers",
|
| 105 |
+
"MiniMaxH3Scheduler",
|
| 106 |
+
{
|
| 107 |
+
"type_hint": [
|
| 108 |
+
"diffusers",
|
| 109 |
+
"MiniMaxH3Scheduler"
|
| 110 |
+
],
|
| 111 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 112 |
+
"subfolder": "audio_scheduler",
|
| 113 |
+
"variant": null,
|
| 114 |
+
"revision": null
|
| 115 |
+
}
|
| 116 |
+
]
|
| 117 |
+
}
|
modular_model_index.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3ModularPipeline",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"_blocks_class_name": "MiniMaxH3Blocks",
|
| 5 |
+
"text_encoder": [
|
| 6 |
+
"transformers",
|
| 7 |
+
"Qwen3VLForConditionalGeneration",
|
| 8 |
+
{
|
| 9 |
+
"type_hint": [
|
| 10 |
+
"transformers",
|
| 11 |
+
"Qwen3VLForConditionalGeneration"
|
| 12 |
+
],
|
| 13 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 14 |
+
"subfolder": "text_encoder",
|
| 15 |
+
"variant": null,
|
| 16 |
+
"revision": null
|
| 17 |
+
}
|
| 18 |
+
],
|
| 19 |
+
"tokenizer": [
|
| 20 |
+
"transformers",
|
| 21 |
+
"Qwen2TokenizerFast",
|
| 22 |
+
{
|
| 23 |
+
"type_hint": [
|
| 24 |
+
"transformers",
|
| 25 |
+
"Qwen2TokenizerFast"
|
| 26 |
+
],
|
| 27 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 28 |
+
"subfolder": "tokenizer",
|
| 29 |
+
"variant": null,
|
| 30 |
+
"revision": null
|
| 31 |
+
}
|
| 32 |
+
],
|
| 33 |
+
"processor": [
|
| 34 |
+
"transformers",
|
| 35 |
+
"Qwen3VLProcessor",
|
| 36 |
+
{
|
| 37 |
+
"type_hint": [
|
| 38 |
+
"transformers",
|
| 39 |
+
"Qwen3VLProcessor"
|
| 40 |
+
],
|
| 41 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 42 |
+
"subfolder": "processor",
|
| 43 |
+
"variant": null,
|
| 44 |
+
"revision": null
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"vae": [
|
| 48 |
+
"diffusers",
|
| 49 |
+
"AutoencoderKLMiniMaxH3",
|
| 50 |
+
{
|
| 51 |
+
"type_hint": [
|
| 52 |
+
"diffusers",
|
| 53 |
+
"AutoencoderKLMiniMaxH3"
|
| 54 |
+
],
|
| 55 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 56 |
+
"subfolder": "vae",
|
| 57 |
+
"variant": null,
|
| 58 |
+
"revision": null
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"audio_vae": [
|
| 62 |
+
"diffusers",
|
| 63 |
+
"AutoencoderKLMiniMaxH3Audio",
|
| 64 |
+
{
|
| 65 |
+
"type_hint": [
|
| 66 |
+
"diffusers",
|
| 67 |
+
"AutoencoderKLMiniMaxH3Audio"
|
| 68 |
+
],
|
| 69 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 70 |
+
"subfolder": "audio_vae",
|
| 71 |
+
"variant": null,
|
| 72 |
+
"revision": null
|
| 73 |
+
}
|
| 74 |
+
],
|
| 75 |
+
"transformer": [
|
| 76 |
+
"diffusers",
|
| 77 |
+
"MiniMaxH3Transformer3DModel",
|
| 78 |
+
{
|
| 79 |
+
"type_hint": [
|
| 80 |
+
"diffusers",
|
| 81 |
+
"MiniMaxH3Transformer3DModel"
|
| 82 |
+
],
|
| 83 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 84 |
+
"subfolder": "transformer",
|
| 85 |
+
"variant": null,
|
| 86 |
+
"revision": null
|
| 87 |
+
}
|
| 88 |
+
],
|
| 89 |
+
"scheduler": [
|
| 90 |
+
"diffusers",
|
| 91 |
+
"MiniMaxH3Scheduler",
|
| 92 |
+
{
|
| 93 |
+
"type_hint": [
|
| 94 |
+
"diffusers",
|
| 95 |
+
"MiniMaxH3Scheduler"
|
| 96 |
+
],
|
| 97 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 98 |
+
"subfolder": "scheduler",
|
| 99 |
+
"variant": null,
|
| 100 |
+
"revision": null
|
| 101 |
+
}
|
| 102 |
+
],
|
| 103 |
+
"audio_scheduler": [
|
| 104 |
+
"diffusers",
|
| 105 |
+
"MiniMaxH3Scheduler",
|
| 106 |
+
{
|
| 107 |
+
"type_hint": [
|
| 108 |
+
"diffusers",
|
| 109 |
+
"MiniMaxH3Scheduler"
|
| 110 |
+
],
|
| 111 |
+
"pretrained_model_name_or_path": "MiniMaxAI/MiniMax-H3",
|
| 112 |
+
"subfolder": "audio_scheduler",
|
| 113 |
+
"variant": null,
|
| 114 |
+
"revision": null
|
| 115 |
+
}
|
| 116 |
+
]
|
| 117 |
+
}
|
processor/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
processor/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
processor/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor/tokenizer_config.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>",
|
| 228 |
+
"<d>",
|
| 229 |
+
"</d>",
|
| 230 |
+
"<|cutoff|>",
|
| 231 |
+
"<|lyrics_start|>",
|
| 232 |
+
"<|lyrics_end|>",
|
| 233 |
+
"<|caption_start|>",
|
| 234 |
+
"<|caption_end|>"
|
| 235 |
+
],
|
| 236 |
+
"bos_token": null,
|
| 237 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 238 |
+
"clean_up_tokenization_spaces": false,
|
| 239 |
+
"eos_token": "<|im_end|>",
|
| 240 |
+
"errors": "replace",
|
| 241 |
+
"model_max_length": 262144,
|
| 242 |
+
"pad_token": "<|endoftext|>",
|
| 243 |
+
"split_special_tokens": false,
|
| 244 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 245 |
+
"unk_token": null
|
| 246 |
+
}
|
processor/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
processor/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3Scheduler",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"shift": 10.0
|
| 5 |
+
}
|
text_encoder/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"image_token_id": 151655,
|
| 6 |
+
"model_type": "qwen3_vl",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 151643,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 151645,
|
| 13 |
+
"head_dim": 128,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 5120,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 25600,
|
| 18 |
+
"max_position_embeddings": 262144,
|
| 19 |
+
"model_type": "qwen3_vl_text",
|
| 20 |
+
"num_attention_heads": 64,
|
| 21 |
+
"num_hidden_layers": 64,
|
| 22 |
+
"num_key_value_heads": 8,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"mrope_interleaved": true,
|
| 26 |
+
"mrope_section": [
|
| 27 |
+
24,
|
| 28 |
+
20,
|
| 29 |
+
20
|
| 30 |
+
],
|
| 31 |
+
"rope_type": "default"
|
| 32 |
+
},
|
| 33 |
+
"rope_theta": 5000000,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 151936
|
| 36 |
+
},
|
| 37 |
+
"tie_word_embeddings": false,
|
| 38 |
+
"transformers_version": "4.57.0.dev0",
|
| 39 |
+
"video_token_id": 151656,
|
| 40 |
+
"vision_config": {
|
| 41 |
+
"deepstack_visual_indexes": [
|
| 42 |
+
8,
|
| 43 |
+
16,
|
| 44 |
+
24
|
| 45 |
+
],
|
| 46 |
+
"depth": 27,
|
| 47 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 48 |
+
"hidden_size": 1152,
|
| 49 |
+
"in_channels": 3,
|
| 50 |
+
"initializer_range": 0.02,
|
| 51 |
+
"intermediate_size": 4304,
|
| 52 |
+
"model_type": "qwen3_vl",
|
| 53 |
+
"num_heads": 16,
|
| 54 |
+
"num_position_embeddings": 2304,
|
| 55 |
+
"out_hidden_size": 5120,
|
| 56 |
+
"patch_size": 16,
|
| 57 |
+
"spatial_merge_size": 2,
|
| 58 |
+
"temporal_patch_size": 2
|
| 59 |
+
},
|
| 60 |
+
"vision_end_token_id": 151653,
|
| 61 |
+
"vision_start_token_id": 151652,
|
| 62 |
+
"num_hidden_layers_override": 50,
|
| 63 |
+
"quantization_config": {
|
| 64 |
+
"quant_method": "nvfp4",
|
| 65 |
+
"activation_scheme": "dynamic",
|
| 66 |
+
"fmt": "e2m1",
|
| 67 |
+
"group_size": 16,
|
| 68 |
+
"scale_fmt": "e4m3",
|
| 69 |
+
"scale_layout": "128x4",
|
| 70 |
+
"modules_to_not_convert": [
|
| 71 |
+
"model.visual",
|
| 72 |
+
"lm_head"
|
| 73 |
+
],
|
| 74 |
+
"producer": {
|
| 75 |
+
"converter": "convert_minimax_h3_text_encoder_nvfp4.py",
|
| 76 |
+
"flashinfer": "0.7.1rc2",
|
| 77 |
+
"kept_language_layers": 50
|
| 78 |
+
}
|
| 79 |
+
}
|
| 80 |
+
}
|
text_encoder/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_encoder/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:969e7d251a873d16d3f487d9a5e82f8901132cfac9344530aa4e25ba9338e9e7
|
| 3 |
+
size 4290567132
|
text_encoder/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff092cd64c489ce4609a08ba5d9f8548591bf835cd98fa4154a7eccd0ea16dfd
|
| 3 |
+
size 4270035088
|
text_encoder/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dab4af0342cfc9b31839458d059327c7cd1e5be1fe779ded253939cabb36a51
|
| 3 |
+
size 4241221712
|
text_encoder/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:628852eb94bd2e3c297d120683f900b49051f236e2cd9d1f26476c30cedc2add
|
| 3 |
+
size 3659204564
|
text_encoder/model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_encoder/preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 16777216,
|
| 4 |
+
"shortest_edge": 65536
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"image_processor_type": "Qwen2VLImageProcessorFast"
|
| 21 |
+
}
|
text_encoder/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
text_encoder/tokenizer_config.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>",
|
| 228 |
+
"<d>",
|
| 229 |
+
"</d>",
|
| 230 |
+
"<|cutoff|>",
|
| 231 |
+
"<|lyrics_start|>",
|
| 232 |
+
"<|lyrics_end|>",
|
| 233 |
+
"<|caption_start|>",
|
| 234 |
+
"<|caption_end|>"
|
| 235 |
+
],
|
| 236 |
+
"bos_token": null,
|
| 237 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 238 |
+
"clean_up_tokenization_spaces": false,
|
| 239 |
+
"eos_token": "<|im_end|>",
|
| 240 |
+
"errors": "replace",
|
| 241 |
+
"model_max_length": 262144,
|
| 242 |
+
"pad_token": "<|endoftext|>",
|
| 243 |
+
"split_special_tokens": false,
|
| 244 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 245 |
+
"unk_token": null
|
| 246 |
+
}
|
text_encoder/video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"size": {
|
| 3 |
+
"longest_edge": 25165824,
|
| 4 |
+
"shortest_edge": 4096
|
| 5 |
+
},
|
| 6 |
+
"patch_size": 16,
|
| 7 |
+
"temporal_patch_size": 2,
|
| 8 |
+
"merge_size": 2,
|
| 9 |
+
"image_mean": [
|
| 10 |
+
0.5,
|
| 11 |
+
0.5,
|
| 12 |
+
0.5
|
| 13 |
+
],
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"processor_class": "Qwen3VLProcessor",
|
| 20 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 21 |
+
}
|
text_encoder/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>",
|
| 228 |
+
"<d>",
|
| 229 |
+
"</d>",
|
| 230 |
+
"<|cutoff|>",
|
| 231 |
+
"<|lyrics_start|>",
|
| 232 |
+
"<|lyrics_end|>",
|
| 233 |
+
"<|caption_start|>",
|
| 234 |
+
"<|caption_end|>"
|
| 235 |
+
],
|
| 236 |
+
"bos_token": null,
|
| 237 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 238 |
+
"clean_up_tokenization_spaces": false,
|
| 239 |
+
"eos_token": "<|im_end|>",
|
| 240 |
+
"errors": "replace",
|
| 241 |
+
"model_max_length": 262144,
|
| 242 |
+
"pad_token": "<|endoftext|>",
|
| 243 |
+
"split_special_tokens": false,
|
| 244 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 245 |
+
"unk_token": null
|
| 246 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "MiniMaxH3Transformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"num_attention_heads": 56,
|
| 5 |
+
"attention_head_dim": 128,
|
| 6 |
+
"hidden_size": 5376,
|
| 7 |
+
"num_layers": 50,
|
| 8 |
+
"num_refiner_layers": 2,
|
| 9 |
+
"ffn_dim": 14336,
|
| 10 |
+
"in_channels": 24,
|
| 11 |
+
"audio_in_channels": 32,
|
| 12 |
+
"patch_size": [
|
| 13 |
+
1,
|
| 14 |
+
2,
|
| 15 |
+
2
|
| 16 |
+
],
|
| 17 |
+
"text_dim": 5120,
|
| 18 |
+
"freq_dim": 256,
|
| 19 |
+
"time_embed_hidden_dim": 5376,
|
| 20 |
+
"time_embed_dim": 2688,
|
| 21 |
+
"rope_freq_dim": 16,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"norm_eps": 1e-05,
|
| 24 |
+
"qk_norm_eps": 1e-05,
|
| 25 |
+
"final_norm_eps": 1e-05,
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"quant_method": "fp8",
|
| 28 |
+
"fmt": "e4m3",
|
| 29 |
+
"weight_scheme": "per_channel",
|
| 30 |
+
"activation_scheme": "dynamic_per_token",
|
| 31 |
+
"quantized_modules": "^transformer_blocks\\.\\d+\\.(attn\\.to_q|attn\\.to_k|attn\\.to_v|attn\\.to_out\\.0|ff\\.net\\.0\\.proj|ff\\.net\\.2)\\.weight$"
|
| 32 |
+
}
|
| 33 |
+
}
|
transformer/diffusion_pytorch_model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c424b75ac2ff48e05e3a4d1526bff9e7d8678481b21d64235bc089b14c6886d
|
| 3 |
+
size 4406761328
|
transformer/diffusion_pytorch_model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6118b7e85336f6d9fa6da8133579d9379bad4a4bbd0e13e4002e2cb9441896a6
|
| 3 |
+
size 3855304928
|
transformer/diffusion_pytorch_model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e6b50b4f038c09b459f590de36d24bb13e025ffdeb6ae5c90c37520b961d23e
|
| 3 |
+
size 3335136944
|
transformer/diffusion_pytorch_model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b217941b37f3f2562c75bcc96f6ccd3fbddb4cfab9fe83e5e718703112e63f28
|
| 3 |
+
size 3855125640
|
transformer/diffusion_pytorch_model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3dca9688f6090e4602c771e683697ded482e899fedbe9c2989ed91327ca600a
|
| 3 |
+
size 3855304904
|
transformer/diffusion_pytorch_model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39948c0641d5818c93aa82e50171ae6c5a583718264cdd89c5258fd9e347e699
|
| 3 |
+
size 3855312080
|
transformer/diffusion_pytorch_model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b40f3bba406f9fe0335757781a68a395e69ea21dfec950c2d89f03430dd0e3fe
|
| 3 |
+
size 3335136960
|
transformer/diffusion_pytorch_model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5045bd70517243a71f4ef9af79236bfcfde8bb882b15fdcb11225d3017abf7f
|
| 3 |
+
size 3855125616
|
transformer/diffusion_pytorch_model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66e81e514eaaff5c67524249bd656c7e27c7a6b89cd3a607662be88b950ddc57
|
| 3 |
+
size 3778177456
|
transformer/diffusion_pytorch_model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2c9e7c001b5753901c328b01ca033a565466e37cf9cbf12fb53edc744e0079a
|
| 3 |
+
size 3855304928
|
transformer/diffusion_pytorch_model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a227b6ac7aee027c940e3b3c7067969f8315aaeafb984040557b5220861fe473
|
| 3 |
+
size 3855312016
|
transformer/diffusion_pytorch_model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3b0514aedb33aaf625bfe4df8c5ae72ca935ab5ec206b50cdcd4c32ed5b842
|
| 3 |
+
size 1368726728
|
transformer/diffusion_pytorch_model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vae/config.json
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLMiniMaxH3",
|
| 3 |
+
"_diffusers_version": "0.36.0.dev0",
|
| 4 |
+
"in_channels": 3,
|
| 5 |
+
"out_channels": 3,
|
| 6 |
+
"latent_channels": 24,
|
| 7 |
+
"block_out_channels": [
|
| 8 |
+
128,
|
| 9 |
+
256,
|
| 10 |
+
256,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
1024
|
| 14 |
+
],
|
| 15 |
+
"layers_per_block": 2,
|
| 16 |
+
"spatial_downsample_factors": [
|
| 17 |
+
2,
|
| 18 |
+
2,
|
| 19 |
+
2,
|
| 20 |
+
2,
|
| 21 |
+
1,
|
| 22 |
+
1
|
| 23 |
+
],
|
| 24 |
+
"temporal_downsample_factors": [
|
| 25 |
+
1,
|
| 26 |
+
2,
|
| 27 |
+
2,
|
| 28 |
+
1,
|
| 29 |
+
1,
|
| 30 |
+
1
|
| 31 |
+
],
|
| 32 |
+
"norm_num_groups": 32,
|
| 33 |
+
"norm_eps": 1e-06,
|
| 34 |
+
"spatial_padding_mode": "reflect",
|
| 35 |
+
"decoder_num_layers": 26,
|
| 36 |
+
"decoder_num_attention_heads": 32,
|
| 37 |
+
"decoder_attention_head_dim": 64,
|
| 38 |
+
"decoder_num_register_tokens": 4,
|
| 39 |
+
"decoder_ffn_mult": 4,
|
| 40 |
+
"decoder_rope_theta": 100.0,
|
| 41 |
+
"decoder_rope_dim_ratio": 0.75,
|
| 42 |
+
"decoder_norm_eps": 1e-05,
|
| 43 |
+
"clip_length": 17,
|
| 44 |
+
"token_drop": 3,
|
| 45 |
+
"latents_mean": [
|
| 46 |
+
0.858090341091156,
|
| 47 |
+
-0.9606591463088989,
|
| 48 |
+
1.0661640167236328,
|
| 49 |
+
-0.5090325474739075,
|
| 50 |
+
-0.2727581858634949,
|
| 51 |
+
-1.3675414323806763,
|
| 52 |
+
-0.2553254961967468,
|
| 53 |
+
-0.26907554268836975,
|
| 54 |
+
-0.5376840829849243,
|
| 55 |
+
-0.0464097298681736,
|
| 56 |
+
0.6657370328903198,
|
| 57 |
+
0.19690127670764923,
|
| 58 |
+
-0.5460608005523682,
|
| 59 |
+
-0.4035342037677765,
|
| 60 |
+
-0.23683024942874908,
|
| 61 |
+
0.25928452610969543,
|
| 62 |
+
-0.30133944749832153,
|
| 63 |
+
0.211341992020607,
|
| 64 |
+
-1.1206848621368408,
|
| 65 |
+
0.3581933379173279,
|
| 66 |
+
-0.04225143790245056,
|
| 67 |
+
0.2604829967021942,
|
| 68 |
+
0.22864092886447906,
|
| 69 |
+
0.7056031823158264
|
| 70 |
+
],
|
| 71 |
+
"latents_std": [
|
| 72 |
+
1.2223774194717407,
|
| 73 |
+
1.2767263650894165,
|
| 74 |
+
1.6831774711608887,
|
| 75 |
+
1.7549455165863037,
|
| 76 |
+
1.5636216402053833,
|
| 77 |
+
2.194143533706665,
|
| 78 |
+
0.9653137922286987,
|
| 79 |
+
1.0569885969161987,
|
| 80 |
+
0.841948926448822,
|
| 81 |
+
0.7729952931404114,
|
| 82 |
+
1.8955937623977661,
|
| 83 |
+
0.946841835975647,
|
| 84 |
+
0.7996809482574463,
|
| 85 |
+
0.44988900423049927,
|
| 86 |
+
0.7197399735450745,
|
| 87 |
+
0.6936293244361877,
|
| 88 |
+
2.961095094680786,
|
| 89 |
+
2.7694199085235596,
|
| 90 |
+
3.0496184825897217,
|
| 91 |
+
2.1088054180145264,
|
| 92 |
+
3.276226282119751,
|
| 93 |
+
3.1627357006073,
|
| 94 |
+
2.2816812992095947,
|
| 95 |
+
2.6127843856811523
|
| 96 |
+
]
|
| 97 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73fc5a61caeba438633eb8f8efd3a57f4915adfa46731a1c991312c724a3b5cc
|
| 3 |
+
size 4225603880
|
vae/minimax_h3_video_vae_int8_convrot.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f11f8b9b96c9dd22b36bc6c18464b6929c207d247e6d865d90fe31588e58e7e2
|
| 3 |
+
size 2137493384
|