jbarrow's picture
EAGLE-3.1 spec-decode head for Chandra-2 (1.36x single-stream, lossless)
d211230 verified
Raw
History Blame Contribute Delete
781 Bytes
{
"architectures": [
"Eagle3LlamaForCausalLM"
],
"model_type": "llama",
"num_hidden_layers": 1,
"hidden_size": 2560,
"intermediate_size": 9216,
"num_attention_heads": 16,
"num_key_value_heads": 4,
"head_dim": 256,
"hidden_act": "silu",
"rms_norm_eps": 1e-06,
"rope_theta": 10000000,
"rope_scaling": null,
"max_position_embeddings": 32768,
"attention_bias": false,
"attention_dropout": 0.0,
"initializer_range": 0.02,
"bos_token_id": 248043,
"eos_token_id": 248044,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"use_cache": true,
"vocab_size": 248320,
"draft_vocab_size": 32768,
"fc_norm": true,
"norm_output": true,
"eagle_aux_hidden_state_layer_ids": [
3,
15,
27
],
"target_hidden_size": 2560
}