Instructions to use VisualInference/P-JiT-21K-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use VisualInference/P-JiT-21K-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download VisualInference/P-JiT-21K-MLX-8bit --local-dir P-JiT-21K-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download text_encoder/config.json from VisualInference/P-JiT-21K-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 2.53 kB
-
https://huggingface.co/VisualInference/P-JiT-21K-MLX-8bit/resolve/main/text_encoder/config.json
- Command line
-
hf download hf://VisualInference/P-JiT-21K-MLX-8bit/text_encoder/config.json
-
curl -L -o config.json https://huggingface.co/VisualInference/P-JiT-21K-MLX-8bit/resolve/main/text_encoder/config.json
2.53 kB
| { | |
| "architectures": [ | |
| "Qwen3_5ForConditionalGeneration" | |
| ], | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5", | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "rms_norm_eps": 1e-06, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 248320, | |
| "mamba_ssm_dtype": "float32", | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "rope_type": "default", | |
| "rope_theta": 10000000, | |
| "partial_rotary_factor": 0.25 | |
| } | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.0.dev0", | |
| "video_token_id": 248057, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053, | |
| "pjit_mlx": { | |
| "format": 1, | |
| "layers": [ | |
| 7, | |
| 15, | |
| 27 | |
| ], | |
| "dtype": "bfloat16", | |
| "quantization": { | |
| "bits": 8, | |
| "group_size": 64 | |
| }, | |
| "embedding": "embed_tokens.safetensors (bf16, read row by row)", | |
| "source": { | |
| "repo": "Qwen/Qwen3.5-4B", | |
| "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a" | |
| } | |
| } | |
| } |