RichardErkhov commited on
Commit
382841e
1 Parent(s): 5c6024d

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HelpingAI-Lite-2x1B",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "bits": 4,
25
+ "group_size": 128,
26
+ "modules_to_not_convert": [
27
+ "gate"
28
+ ],
29
+ "quant_method": "awq",
30
+ "version": "gemm",
31
+ "zero_point": true
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 10000.0,
36
+ "router_aux_loss_coef": 0.001,
37
+ "router_jitter_noise": 0.0,
38
+ "sliding_window": null,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.46.3",
42
+ "use_cache": false,
43
+ "vocab_size": 32000
44
+ }