Instructions to use freestuff2875/GLM-Image-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use freestuff2875/GLM-Image-bnb-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("freestuff2875/GLM-Image-bnb-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update vision_language_encoder/config.json
Browse files
vision_language_encoder/config.json
CHANGED
|
@@ -17,49 +17,6 @@
|
|
| 17 |
"llm_int8_enable_fp32_cpu_offload": false,
|
| 18 |
"llm_int8_has_fp16_weight": false,
|
| 19 |
"llm_int8_skip_modules": [
|
| 20 |
-
"transformer_blocks.0.norm1.linear.weight",
|
| 21 |
-
"time_condition_embed",
|
| 22 |
-
"image_projector",
|
| 23 |
-
"proj_out",
|
| 24 |
-
"prior_projector",
|
| 25 |
-
"glyph_projector",
|
| 26 |
-
"norm_out",
|
| 27 |
-
"transformer_blocks.23.norm1.linear.weight",
|
| 28 |
-
"transformer_blocks.24.norm1.linear.weight",
|
| 29 |
-
"transformer_blocks.25.norm1.linear.weight",
|
| 30 |
-
"transformer_blocks.0.attn1.to_k.weight",
|
| 31 |
-
"transformer_blocks.0.attn1.to_v.weight",
|
| 32 |
-
"transformer_blocks.0.ff.net.0.proj.weight",
|
| 33 |
-
"transformer_blocks.1.attn1.to_k.weight",
|
| 34 |
-
"transformer_blocks.1.attn1.to_q.weight",
|
| 35 |
-
"transformer_blocks.1.attn1.to_v.weight",
|
| 36 |
-
"transformer_blocks.1.ff.net.0.proj.weight",
|
| 37 |
-
"transformer_blocks.10.attn1.to_v.weight",
|
| 38 |
-
"transformer_blocks.2.attn1.to_k.weight",
|
| 39 |
-
"transformer_blocks.2.attn1.to_q.weight",
|
| 40 |
-
"transformer_blocks.2.attn1.to_v.weight",
|
| 41 |
-
"transformer_blocks.3.attn1.to_k.weight",
|
| 42 |
-
"transformer_blocks.3.attn1.to_q.weight",
|
| 43 |
-
"transformer_blocks.3.attn1.to_v.weight",
|
| 44 |
-
"transformer_blocks.3.ff.net.0.proj.weight",
|
| 45 |
-
"transformer_blocks.4.attn1.to_k.weight",
|
| 46 |
-
"transformer_blocks.4.attn1.to_q.weight",
|
| 47 |
-
"transformer_blocks.4.attn1.to_v.weight",
|
| 48 |
-
"transformer_blocks.5.attn1.to_v.weight",
|
| 49 |
-
"transformer_blocks.6.attn1.to_v.weight",
|
| 50 |
-
"transformer_blocks.7.attn1.to_v.weight",
|
| 51 |
-
"transformer_blocks.8.attn1.to_v.weight",
|
| 52 |
-
"transformer_blocks.9.attn1.to_v.weight",
|
| 53 |
-
"transformer_blocks.21.norm1.linear.weight",
|
| 54 |
-
"transformer_blocks.22.norm1.linear.weight",
|
| 55 |
-
"transformer_blocks.25.ff.net.2.weight",
|
| 56 |
-
"transformer_blocks.26.attn1.to_v.weight",
|
| 57 |
-
"transformer_blocks.26.ff.net.2.weight",
|
| 58 |
-
"transformer_blocks.26.norm1.linear.weight",
|
| 59 |
-
"transformer_blocks.27.attn1.to_v.weight",
|
| 60 |
-
"transformer_blocks.27.norm1.linear.weight",
|
| 61 |
-
"transformer_blocks.28.attn1.to_v.weight",
|
| 62 |
-
"transformer_blocks.29.attn1.to_v.weight",
|
| 63 |
"vqmodel",
|
| 64 |
"lm_head",
|
| 65 |
"embeddings",
|
|
|
|
| 17 |
"llm_int8_enable_fp32_cpu_offload": false,
|
| 18 |
"llm_int8_has_fp16_weight": false,
|
| 19 |
"llm_int8_skip_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"vqmodel",
|
| 21 |
"lm_head",
|
| 22 |
"embeddings",
|