MeowFET
init: add model checkpoint
dfe1832
raw
history blame contribute delete
838 Bytes
{
"_name_or_path": "/mnt/kaiwu-group-pp-sh/edge_llm/pruned_hf/7b_instruct_to_4b_c4_eli5_top_5_percent_alpaca_95_05/iter_2048",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 12288,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 20,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_lm_head": false,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}