gate369's picture
Training in progress, step 1000
eaa8d3a verified
raw
history blame contribute delete
No virus
665 Bytes
{
"_name_or_path": "liminerity/Bitnet-Mistral.0.2-330m-v0.2-grokfast",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 1024,
"max_position_embeddings": 4096,
"model_type": "mistral",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32000
}