dominguesm commited on
Commit
d0f4870
1 Parent(s): 3375539

Upload MambaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +33 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./mambarim-110M",
3
+ "architectures": [
4
+ "MambaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "conv_kernel": 4,
8
+ "eos_token_id": 2,
9
+ "expand": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.1,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "model_type": "mamba",
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 3,
18
+ "rescale_prenorm_residual": false,
19
+ "residual_in_fp32": true,
20
+ "state_size": 16,
21
+ "time_step_floor": 0.0001,
22
+ "time_step_init_scheme": "random",
23
+ "time_step_max": 0.1,
24
+ "time_step_min": 0.001,
25
+ "time_step_rank": 48,
26
+ "time_step_scale": 1.0,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.39.0.dev0",
29
+ "use_bias": false,
30
+ "use_cache": true,
31
+ "use_conv_bias": true,
32
+ "vocab_size": 32000
33
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19dbe1e76f6b6e6824959ce58b87ea1cc8ec5165b66ba99d9c20db1e871bfb19
3
+ size 279359288