adarshxs's picture
adarshxs HF Staff
EAGLE3 draft model for sarvam-30b (epoch 0, step 30000)
b9156a4 verified
raw
history blame contribute delete
844 Bytes
{
"architectures": [
"LlamaForCausalLMEagle3"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"draft_vocab_size": 32000,
"dtype": "bfloat16",
"eagle_config": {
"eagle_aux_hidden_state_layer_ids": [
1,
9,
17
],
"use_aux_hidden_state": true
},
"eos_token_id": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 1,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 8000000.0,
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 262144
}