Update README.md

README.md

@@ -4,6 +4,8 @@ base_model:
 - genmo/mochi-1-preview
 ---
 
+**Please change bf16 to fp16 in your code. I've just changed the checkpoint to fp16, which appears more coherent with mochi**
+
 This is a nf4 quantization of mochi-1-preview. It excludes specific layers that allow it to stay coherent:
 
 bf16
@@ -27,8 +29,8 @@ To use:
 ```
 from diffusers import MochiPipeline, MochiTransformer3DModel
 from diffusers.utils import export_to_video
-transformer = MochiTransformer3DModel.from_pretrained("imnotednamode/mochi-1-preview-mix-nf4-small", torch_dtype=torch.bfloat16)
-pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", torch_dtype=torch.bfloat16, transformer=transformer)
+transformer = MochiTransformer3DModel.from_pretrained("imnotednamode/mochi-1-preview-mix-nf4-small", torch_dtype=torch.float16)
+pipe = MochiPipeline.from_pretrained("genmo/mochi-1-preview", torch_dtype=torch.float16, transformer=transformer)
 pipe.enable_model_cpu_offload()
 pipe.enable_vae_tiling()
 frames = pipe("A camera follows a squirrel running around on a tree branch", num_inference_steps=100, guidance_scale=4.5, height=480, width=848, num_frames=161).frames[0]
@@ -41,8 +43,8 @@ To reproduce:
 ```
 from diffusers import MochiPipeline, MochiTransformer3DModel, BitsAndBytesConfig
 import torch
-quantization_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_quant_type="nf4", llm_int8_skip_modules=["final_layer", "x_embedder.proj", "t_embedder", "pos_frequencies", "t5"])
+quantization_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16, bnb_4bit_quant_type="nf4", llm_int8_skip_modules=["final_layer", "x_embedder.proj", "t_embedder", "pos_frequencies", "t5"])
 # Please convert mochi to diffusers first
-transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", variant="refs/pr/18", subfolder="transformer", quantization_config=quantization_config, torch_dtype=torch.bfloat16)
+transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", variant="refs/pr/18", subfolder="transformer", quantization_config=quantization_config, torch_dtype=torch.float16)
 transformer.save_pretrained("mochi-1-preview-nf4")
 ```