Instructions to use Intel/GLM-Image-int4-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Intel/GLM-Image-int4-AutoRound with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Intel/GLM-Image-int4-AutoRound", 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
- Draw Things
- DiffusionBee
| { | |
| "architectures": [ | |
| "GlmImageForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_end_token_id": 16385, | |
| "image_start_token_id": 16384, | |
| "image_token_id": 167855, | |
| "model_type": "glm_image", | |
| "quantization_config": { | |
| "autoround_version": "0.12.0", | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "data_type": "int", | |
| "group_size": 128, | |
| "packing_format": "auto_round:auto_gptq", | |
| "quant_method": "auto-round", | |
| "sym": true | |
| }, | |
| "text_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 16385, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "max_position_embeddings": 131072, | |
| "model_type": "glm_image_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 167841, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 8, | |
| 12, | |
| 12 | |
| ], | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 10000, | |
| "rope_type": "default" | |
| }, | |
| "use_cache": true, | |
| "vision_vocab_size": 16512, | |
| "vocab_size": 168064 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.3.0", | |
| "vision_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "depth": 40, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu", | |
| "hidden_size": 1536, | |
| "image_size": 2048, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "glm_image_vision", | |
| "num_heads": 16, | |
| "patch_size": 16, | |
| "spatial_merge_size": 1 | |
| }, | |
| "vq_config": { | |
| "dtype": "bfloat16", | |
| "embed_dim": 2048, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "latent_channels": 1536, | |
| "model_type": "glm_image_vqmodel", | |
| "num_embeddings": 16384 | |
| } | |
| } | |