Instructions to use changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-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("changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-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 Settings
- Draw Things
- DiffusionBee
Download text_encoder/config.json from changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 1.91 kB
-
https://huggingface.co/changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/changwangss/FLUX.2-dev-MXFP8-RTN-FullEncoder-AutoRound/resolve/main/text_encoder/config.json
1.91 kB
| { | |
| "architectures": [ | |
| "Mistral3ForConditionalGeneration" | |
| ], | |
| "dtype": "bfloat16", | |
| "image_token_index": 10, | |
| "model_type": "mistral3", | |
| "multimodal_projector_bias": false, | |
| "projector_hidden_act": "gelu", | |
| "spatial_merge_size": 2, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32768, | |
| "max_position_embeddings": 131072, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000000.0, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "transformers_version": "4.57.1", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "image_size": 1540, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "pixtral", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "rope_theta": 10000.0 | |
| }, | |
| "vision_feature_layer": -1, | |
| "quantization_config": { | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:llm_compressor", | |
| "bits": 8, | |
| "group_size": 32, | |
| "sym": true, | |
| "data_type": "mx_fp", | |
| "iters": 0, | |
| "model_free": true, | |
| "autoround_version": "0.17.0", | |
| "enable_quanted_input": false, | |
| "block_name_to_quantize": "language_model.model.layers,vision_tower.transformer.layers", | |
| "act_bits": 8, | |
| "act_data_type": "mx_fp", | |
| "act_dynamic": true, | |
| "act_group_size": 32, | |
| "act_sym": true, | |
| "extra_config": { | |
| "language_model.lm_head": { | |
| "bits": 16, | |
| "data_type": "float", | |
| "act_bits": 16, | |
| "act_data_type": "float" | |
| } | |
| } | |
| } | |
| } |