Qubitium commited on
Commit
051a848
1 Parent(s): 5a048a8

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +52 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/monster/data/model/dbrx-base-converted-v2/",
3
+ "architectures": [
4
+ "DbrxForCausalLM"
5
+ ],
6
+ "attn_config": {
7
+ "clip_qkv": 8,
8
+ "kv_n_heads": 8,
9
+ "model_type": "",
10
+ "rope_theta": 500000
11
+ },
12
+ "auto_map": {
13
+ "AutoConfig": "configuration_dbrx.DbrxConfig",
14
+ "AutoModelForCausalLM": "modeling_dbrx.DbrxForCausalLM"
15
+ },
16
+ "d_model": 6144,
17
+ "emb_pdrop": 0.0,
18
+ "ffn_config": {
19
+ "ffn_hidden_size": 10752,
20
+ "model_type": "",
21
+ "moe_jitter_eps": 0.01,
22
+ "moe_loss_weight": 0.05,
23
+ "moe_num_experts": 16,
24
+ "moe_top_k": 4
25
+ },
26
+ "initializer_range": 0.02,
27
+ "max_seq_len": 32768,
28
+ "model_type": "dbrx",
29
+ "n_heads": 48,
30
+ "n_layers": 40,
31
+ "output_router_logits": false,
32
+ "quantization_config": {
33
+ "bits": 4,
34
+ "checkpoint_format": "marlin",
35
+ "damp_percent": 0.005,
36
+ "desc_act": false,
37
+ "group_size": 128,
38
+ "model_file_base_name": null,
39
+ "model_name_or_path": null,
40
+ "quant_method": "gptq",
41
+ "static_groups": false,
42
+ "sym": true,
43
+ "true_sequential": true
44
+ },
45
+ "resid_pdrop": 0.0,
46
+ "router_aux_loss_coef": 0.05,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "float16",
49
+ "transformers_version": "4.38.2",
50
+ "use_cache": true,
51
+ "vocab_size": 100352
52
+ }