BK-Lee commited on
Commit
2953130
1 Parent(s): d5e6963

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +43 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "state-spaces/mamba-130m-hf",
3
+ "architectures": [
4
+ "MeteorMambaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "conv_kernel": 4,
8
+ "d_inner": 1536,
9
+ "d_model": 768,
10
+ "eos_token_id": 0,
11
+ "expand": 2,
12
+ "fused_add_norm": true,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 768,
15
+ "ignore_index": -100,
16
+ "image_token_index": 92544,
17
+ "initializer_range": 0.1,
18
+ "intermediate_size": 1536,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "mamba",
21
+ "n_layer": 24,
22
+ "num_hidden_layers": 24,
23
+ "pad_token_id": 0,
24
+ "pad_vocab_size_multiple": 8,
25
+ "rescale_prenorm_residual": false,
26
+ "residual_in_fp32": true,
27
+ "rms_norm": true,
28
+ "ssm_cfg": {},
29
+ "state_size": 16,
30
+ "time_step_floor": 0.0001,
31
+ "time_step_init_scheme": "random",
32
+ "time_step_max": 0.1,
33
+ "time_step_min": 0.001,
34
+ "time_step_rank": 48,
35
+ "time_step_scale": 1.0,
36
+ "tor_token_index": 92545,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.40.2",
39
+ "use_bias": false,
40
+ "use_cache": true,
41
+ "use_conv_bias": true,
42
+ "vocab_size": 50280
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.40.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9cfdf148f6dae1b44359794e6bd5bf2825d58793abf39bf0efe6423f05a798
3
+ size 886105400