d0rj's picture
feat: Initial commit, epoch 5 (best ckpt)
53d8d18
Raw
History Blame Contribute Delete
2.12 kB
{
"architectures": [
"DFlashDraftModel"
],
"auto_map": {
"": "config.DFlashSpeculatorConfig"
},
"aux_hidden_state_layer_ids": [
2,
7,
13,
18,
21
],
"block_size": 8,
"draft_vocab_size": 32000,
"dtype": "bfloat16",
"mask_token_id": 4,
"max_anchors": 256,
"sliding_window_non_causal": false,
"speculators_config": {
"algorithm": "dflash",
"default_proposal_method": "greedy",
"proposal_methods": [
{
"accept_tolerance": 0.0,
"proposal_type": "greedy",
"speculative_tokens": 7,
"verifier_accept_k": 1
}
],
"verifier": {
"architectures": [
"T5Gemma2ForConditionalGeneration"
],
"name_or_path": "google/t5gemma-2-1b-1b"
}
},
"speculators_model_type": "dflash",
"speculators_version": "0.7.0.dev11",
"target_hidden_size": null,
"tie_word_embeddings": false,
"transformer_layer_config": {
"architectures": [
"T5Gemma2ForConditionalGeneration"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 6912,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 4,
"num_hidden_layers": 5,
"num_key_value_heads": 1,
"pad_token_id": null,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"factor": 8.0,
"rope_theta": 1000000,
"rope_type": "linear"
},
"rope_theta": 1000000,
"sliding_window": 2048,
"tie_word_embeddings": false,
"use_cache": true,
"verifier_final_logit_softcapping": null,
"verifier_hidden_states_are_normalized": true,
"verifier_is_encoder_decoder": true,
"verifier_model_type": "t5gemma2",
"vocab_size": 262144
},
"transformers_version": "5.12.1"
}