Instructions to use SubconsciousDev/glm-5.2-fp8-dflash-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SubconsciousDev/glm-5.2-fp8-dflash-v2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("SubconsciousDev/glm-5.2-fp8-dflash-v2") model = AutoModel.from_pretrained("SubconsciousDev/glm-5.2-fp8-dflash-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "DFlashDraftModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "block_size": 12, | |
| "bos_token_id": null, | |
| "dflash_config": { | |
| "block_size": 12, | |
| "mask_token_id": 154821, | |
| "num_target_layers": 78, | |
| "target_layer_ids": [ | |
| 1, | |
| 16, | |
| 31, | |
| 45, | |
| 60, | |
| 75 | |
| ] | |
| }, | |
| "dtype": "bfloat16", | |
| "eos_token_id": null, | |
| "head_dim": 96, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 1048576, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 8, | |
| "num_target_layers": 78, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 1000000.0, | |
| "rope_type": "default" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.6.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 154880 | |
| } | |