Downloads · 30 days
0
CogView4-6B-quanto_int8
p1atdev/CogView4-6B-quanto_int8
CogView4-6B-quanto_int8 is a machine learning model from p1atdev. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
- vae.: torch.bfloat16. No quantization. - textencoder.layers.: - Int8 with Optimum Quanto - Target layers:["qproj", "kproj", "vproj", "oproj", "mlp.downproj", "mlp.gateupproj"] - diffusionmodel.: - Int8 with Optimum…
Access
Public
Updated Mar 8, 2025
Repo size
17.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors17.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 8, 2025
- Updated
- Mar 8, 2025
- SHA
- b08d6600
Base models
Model card
From the Hugging Face model README
Quantization settings
vae.:torch.bfloat16. No quantization.text_encoder.layers.:- Int8 with Optimum Quanto
- Target layers:
["q_proj", "k_proj", "v_proj", "o_proj", "mlp.down_proj", "mlp.gate_up_proj"]
diffusion_model.:- Int8 with Optimum Quanto
- Target layers:
["to_q", "to_k", "to_v", "to_out.0", "ff.net.0.proj", "ff.net.2"]
VRAM cosumption
- Text encoder (
text_encoder.): about 11 GB - Denoiser (
diffusion_model.): about 10 GB
Samples
torch.bfloat16 | Quanto Int8 |
|---|---|
| <img src="./images/sample_bf16_01.jpg" width="320px" /> | <img src="./images/sample_quanto_01.jpg" width="320px" /> |
| VRAM 40GB (without offloading) | VRAM 28GB (without offloading) |
- prompt:
""" A photo of a nendoroid figure of hatsune miku holding a sign that says "CogView4" """" - negative_prompt:
"blurry, low quality, horror" - height:
1152 - width:
1152 - cfg_scale:
3.5 - num_inference_steps:
20
- License
- apache-2.0
- Created
- Mar 8, 2025
- Updated
- Mar 8, 2025