Feature Extraction
Transformers
Safetensors
qwen3
speculative-decoding
dflash
eagle
draft-model
kimi-k2
specforge
custom_code
Instructions to use cm00cm/Kimi-K2.7-Code-DFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cm00cm/Kimi-K2.7-Code-DFlash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="cm00cm/Kimi-K2.7-Code-DFlash", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("cm00cm/Kimi-K2.7-Code-DFlash", trust_remote_code=True) model = AutoModel.from_pretrained("cm00cm/Kimi-K2.7-Code-DFlash", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "DFlashDraftModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoModel": "dflash.DFlashDraftModel" | |
| }, | |
| "block_size": 8, | |
| "bos_token_id": null, | |
| "dflash_config": { | |
| "mask_token_id": 163838, | |
| "target_layer_ids": [ | |
| 1, | |
| 12, | |
| 24, | |
| 35, | |
| 47, | |
| 58 | |
| ] | |
| }, | |
| "dtype": "bfloat16", | |
| "eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "mask_token_id": 163838, | |
| "max_position_embeddings": 262144, | |
| "max_window_layers": 6, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 8, | |
| "num_target_layers": 61, | |
| "pad_token_id": null, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "beta_fast": 32.0, | |
| "beta_slow": 1.0, | |
| "factor": 64.0, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 4096, | |
| "rope_theta": 50000.0, | |
| "rope_type": "yarn", | |
| "type": "yarn" | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.3.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 163840 | |
| } | |