yujiepan commited on
Commit
d1dc452
1 Parent(s): e9af3b7

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -6,12 +6,12 @@
6
  "bos_token_id": 0,
7
  "conv_kernel": 4,
8
  "eos_token_id": 0,
9
- "expand": 2,
10
  "fused_add_norm": true,
11
  "hidden_act": "silu",
12
- "hidden_size": 4,
13
  "initializer_range": 0.1,
14
- "intermediate_size": 6,
15
  "layer_norm_epsilon": 1e-05,
16
  "model_type": "mamba",
17
  "n_layer": 2,
@@ -21,17 +21,18 @@
21
  "rescale_prenorm_residual": false,
22
  "residual_in_fp32": true,
23
  "rms_norm": true,
24
- "state_size": 16,
25
  "time_step_floor": 0.0001,
26
  "time_step_init_scheme": "random",
27
  "time_step_max": 0.1,
28
  "time_step_min": 0.001,
29
  "time_step_rank": 160,
30
  "time_step_scale": 1.0,
31
- "torch_dtype": "float16",
32
- "transformers_version": "4.39.2",
33
  "use_bias": false,
34
  "use_cache": true,
35
  "use_conv_bias": true,
 
36
  "vocab_size": 50280
37
  }
 
6
  "bos_token_id": 0,
7
  "conv_kernel": 4,
8
  "eos_token_id": 0,
9
+ "expand": 4,
10
  "fused_add_norm": true,
11
  "hidden_act": "silu",
12
+ "hidden_size": 8,
13
  "initializer_range": 0.1,
14
+ "intermediate_size": 32,
15
  "layer_norm_epsilon": 1e-05,
16
  "model_type": "mamba",
17
  "n_layer": 2,
 
21
  "rescale_prenorm_residual": false,
22
  "residual_in_fp32": true,
23
  "rms_norm": true,
24
+ "state_size": 8,
25
  "time_step_floor": 0.0001,
26
  "time_step_init_scheme": "random",
27
  "time_step_max": 0.1,
28
  "time_step_min": 0.001,
29
  "time_step_rank": 160,
30
  "time_step_scale": 1.0,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.45.2",
33
  "use_bias": false,
34
  "use_cache": true,
35
  "use_conv_bias": true,
36
+ "use_mambapy": false,
37
  "vocab_size": 50280
38
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.39.2"
7
  }
 
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.45.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08b7c8f8088e61205f8f12b807186900608972bad5daa99a99623095580ecc99
3
- size 413736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dda3cbb122b916339e098328b1f09506d276e2be8d65f01a3555c44e40ab5a13
3
+ size 855760
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {