Add files using upload-large-folder tool

README.md

@@ -0,0 +1,51 @@
+# Ovi FusionModel - FP8 Quantized
+
+This is the Ovi FusionModel quantized with FP8 (e4m3_e4m3_dynamic_per_tensor) for faster inference.
+
+## Quantization Details
+
+- **Video Model Blocks**: 30 blocks quantized
+- **Audio Model Blocks**: 30 blocks quantized
+- **Attention/FFN layers**: e4m3_e4m3_dynamic_per_tensor
+- **Other layers**: e4m3_weightonly
+
+## Usage
+
+```python
+import sys
+import os
+import torch
+from omegaconf import OmegaConf
+from huggingface_hub import hf_hub_download
+
+OVI_PATH = "./workspace/Ovi"
+sys.path.insert(0, OVI_PATH)
+os.chdir(OVI_PATH)
+
+from ovi.ovi_fusion_engine import OviFusionEngine
+
+# Download quantized weights
+model_path = hf_hub_download(
+    repo_id="wavespeed/Ovi-e4m3_e4m3_dynamic_per_tensor",
+    filename="model.pth"
+)
+
+config = OmegaConf.load("config.yaml")
+engine = OviFusionEngine(config=config, device="cuda", target_dtype=torch.bfloat16)
+
+# Load quantized weights
+engine.model.load_state_dict(torch.load(model_path))
+
+# Model is already quantized, ready for inference
+```
+
+## Model Card
+
+- **Developed by**: Alibaba/Character.AI
+- **Model type**: Video + Audio generation (FusionModel)
+- **Quantization**: FP8 (e4m3_e4m3_dynamic_per_tensor)
+- **License**: Check original Ovi repository
+
+## Original Model
+
+Based on [Ovi](https://github.com/character-ai/Ovi)

config.yaml

@@ -0,0 +1,15 @@
+ckpt_dir: /home/zeyi/repos/model-deploy/workspace/Ovi/ckpts
+mode: t2v
+output_dir: /tmp
+seed: 0
+solver_name: unipc
+num_steps: 20
+shift: 5.0
+video_guidance_scale: 4.0
+audio_guidance_scale: 3.0
+slg_layer: 11
+video_negative_prompt: ''
+audio_negative_prompt: ''
+each_example_n_times: 1
+sp_size: 1
+cpu_offload: false

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a7c2509b5439ca10a29e154b031718778712dd9b8c7c044dc7ee59278048f3
+size 12377521691