Openhermes-7b-E8P-2Bit / config.json
at676's picture
abb933438870b175e0870193de476afa97b31056ad597cf3f4a82dccea39ff24
35e9e68
raw
history blame
840 Bytes
{
"_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"quip_params": {
"codebook": "E8P12",
"codesz": 8,
"fused": true,
"idx_dtype": "torch.int16",
"lora_rank": 0,
"outlier_channel_split": false,
"packsz": 1,
"rescale_WH": false
},
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.0",
"use_cache": false,
"vocab_size": 32002
}