fmasterpro27 commited on
Commit
64cf456
·
verified ·
1 Parent(s): e7500eb

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +72 -0
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": true,
6
+ "block_dim": 2048,
7
+ "block_ff_dim": 12288,
8
+ "block_ffn_dim_multiplier": 1.0,
9
+ "block_mlp_init_scale": 1.0,
10
+ "block_multiple_of": 256,
11
+ "block_norm_eps": 1e-05,
12
+ "block_out_init_scale": 1.0,
13
+ "block_use_swiglu": true,
14
+ "block_use_xavier_init": true,
15
+ "bos_token_id": 1,
16
+ "conv_L_cache": 3,
17
+ "conv_bias": false,
18
+ "conv_dim": 2048,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "float16",
21
+ "eos_token_id": 7,
22
+ "hidden_size": 2048,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 12288,
25
+ "layer_types": [
26
+ "conv",
27
+ "conv",
28
+ "full_attention",
29
+ "conv",
30
+ "conv",
31
+ "full_attention",
32
+ "conv",
33
+ "conv",
34
+ "full_attention",
35
+ "conv",
36
+ "full_attention",
37
+ "conv",
38
+ "full_attention",
39
+ "conv",
40
+ "full_attention",
41
+ "conv"
42
+ ],
43
+ "max_position_embeddings": 128000,
44
+ "model_type": "lfm2",
45
+ "norm_eps": 1e-05,
46
+ "num_attention_heads": 32,
47
+ "num_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 0,
51
+ "quantization_config": {
52
+ "_load_in_4bit": false,
53
+ "_load_in_8bit": true,
54
+ "bnb_4bit_compute_dtype": "float32",
55
+ "bnb_4bit_quant_storage": "uint8",
56
+ "bnb_4bit_quant_type": "fp4",
57
+ "bnb_4bit_use_double_quant": false,
58
+ "llm_int8_enable_fp32_cpu_offload": false,
59
+ "llm_int8_has_fp16_weight": false,
60
+ "llm_int8_skip_modules": null,
61
+ "llm_int8_threshold": 6.0,
62
+ "load_in_4bit": false,
63
+ "load_in_8bit": true,
64
+ "quant_method": "bitsandbytes"
65
+ },
66
+ "rope_theta": 1000000.0,
67
+ "tie_embedding": true,
68
+ "transformers_version": "4.57.3",
69
+ "use_cache": true,
70
+ "use_pos_enc": true,
71
+ "vocab_size": 65536
72
+ }