voidful commited on
Commit
2dbd746
1 Parent(s): b6c998e

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "voidful/mamba-790m-base",
3
+ "architectures": [
4
+ "MambaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "conv_kernel": 4,
8
+ "d_model": 2048,
9
+ "eos_token_id": 0,
10
+ "expand": 2,
11
+ "fused_add_norm": true,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "initializer_range": 0.1,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "model_type": "mamba",
18
+ "n_layer": 48,
19
+ "num_hidden_layers": 48,
20
+ "pad_token_id": 0,
21
+ "pad_vocab_size_multiple": 8,
22
+ "rescale_prenorm_residual": false,
23
+ "residual_in_fp32": true,
24
+ "rms_norm": true,
25
+ "ssm_cfg": {},
26
+ "state_size": 16,
27
+ "time_step_floor": 0.0001,
28
+ "time_step_init_scheme": "random",
29
+ "time_step_max": 0.1,
30
+ "time_step_min": 0.001,
31
+ "time_step_rank": 96,
32
+ "time_step_scale": 1.0,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.39.3",
35
+ "use_bias": false,
36
+ "use_cache": true,
37
+ "use_conv_bias": true,
38
+ "vocab_size": 80961
39
+ }
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": "4.39.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfae45488d2bda35b88cbb1a9e326fc52f2d2a4b69fa85263df859b8c45b55ae
3
+ size 1685432032
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e129e28e4ed15ac0c3ca7802fb1bfd9b703ca9a023803fe5ee1d6b26e602e509
3
+ size 9880887
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ae1347774c0749a55025376e801f5e4dc34af975a2a09aec28b6f4540c1edd
3
+ size 14512
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d1ee2970895440f8d97f069224d964db0d54cae0cc255eb387cb4bdcb265fa
3
+ size 14512
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f35e328ce33598fc8a5cacebc00a00411c322ddb9ef556c07f91b8b9669281
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bb5155194e16f40dfff5ee2b78fbbb75f5bf74f8fb0faab091eb7c94ab3f14
3
+ size 4920