ngocbh's picture
Upload folder using huggingface_hub
f1f7745 verified
{
"architectures": [
"TrimKVLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_impl": "rg_attn_flex",
"base_loss": "fwkl_ntp",
"base_model": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
"bos_token_id": 128000,
"buffer_size": 1,
"compress_memory": true,
"compress_strategy": "alpha",
"dtype": "bfloat16",
"eos_token_id": 128001,
"floor_budget_ratio": 0.0,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"logit_block_size": 8192,
"max_position_embeddings": 131072,
"max_seq_len": 32768,
"memory_size": 512.0,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"retention_gate": "rg",
"retention_gate_bias_init": 8.0,
"retention_gate_intermediate_size": 512,
"retention_weight": 1.0,
"rg_dropout": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"skip_layers": 0,
"tie_word_embeddings": false,
"trainable_params": "self_attn.retention_gate",
"transformers_version": "4.57.0",
"use_cache": false,
"vocab_size": 128256
}