File size: 1,635 Bytes
62e9855 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
{
"_name_or_path": "biomap-research/xtrimopglm-100b-int4",
"add_bias_linear": true,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": true,
"architectures": [
"xTrimoPGLMModel"
],
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"auto_map": {
"AutoConfig": "configuration_xtrimopglm.xTrimoPGLMConfig",
"AutoModel": "modeling_xtrimopglm.xTrimoPGLMForMaskedLM",
"AutoModelForCausalLM": "modeling_xtrimopglm.xTrimoPGLMForCasualLM",
"AutoModelForMaskedLM": "modeling_xtrimopglm.xTrimoPGLMForMaskedLM",
"AutoModelForSequenceClassification": "modeling_xtrimopglm.xTrimoPGLMForSequenceClassification",
"AutoModelForTokenClassification": "modeling_xtrimopglm.xTrimoPGLMForTokenClassification"
},
"bias_dropout_fusion": true,
"deepnorm": true,
"experts_per_token": 0,
"ffn_hidden_size": 31744,
"fp32_residual_connection": false,
"glu_activation": "geglu",
"initializer_range": 0.02,
"head_num": 1,
"hidden_dropout": 0.0,
"hidden_size": 10240,
"is_causal": false,
"use_cache":true,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"model_type": "xTrimoPGLM",
"moe": false,
"multi_query_attention": false,
"multi_query_group_num": 1,
"num_attention_heads": 80,
"num_experts": 0,
"num_layers": 72,
"padded_vocab_size": 128,
"post_layer_norm": true,
"quantization_bit": 4,
"rmsnorm": false,
"rotary_embedding_2d": true,
"seq_length": 2048,
"torch_dtype": "float32",
"transformers_version": "4.41.2",
"untie_head": false,
"use_pytorch_sdpa": true,
"vocab_size": 128
}
|