Transformers
Safetensors
llama
speculative-decoding
eagle3
eagle
draft-model
kimi-k2
specforge
text-generation-inference
Instructions to use cm00cm/Kimi-K2.7-Code-EAGLE3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cm00cm/Kimi-K2.7-Code-EAGLE3 with Transformers:
# Load model directly from transformers import AutoTokenizer, LlamaForCausalLMEagle3 tokenizer = AutoTokenizer.from_pretrained("cm00cm/Kimi-K2.7-Code-EAGLE3") model = LlamaForCausalLMEagle3.from_pretrained("cm00cm/Kimi-K2.7-Code-EAGLE3") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "LlamaForCausalLMEagle3" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 163584, | |
| "draft_vocab_size": 32000, | |
| "dtype": "bfloat16", | |
| "eagle_config": { | |
| "eagle_aux_hidden_state_layer_ids": [ | |
| 1, | |
| 29, | |
| 57 | |
| ], | |
| "use_aux_hidden_state": true | |
| }, | |
| "eos_token_id": 163586, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 40960, | |
| "max_position_embeddings": 163840, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 56, | |
| "num_hidden_layers": 1, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 163839, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.3.0", | |
| "use_cache": true, | |
| "vocab_size": 163840 | |
| } | |