pszemraj commited on
Commit
86fd939
1 Parent(s): 6110e85

Training in progress, step 100

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_block_types": [
3
+ "recurrent",
4
+ "recurrent",
5
+ "attention"
6
+ ],
7
+ "_name_or_path": "pszemraj/griffin-v0.01-c3t-8layer-simplewiki-silu",
8
+ "architectures": [
9
+ "RecurrentGemmaForCausalLM"
10
+ ],
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "attention_window_size": 2048,
14
+ "block_types": [
15
+ "recurrent",
16
+ "recurrent",
17
+ "attention"
18
+ ],
19
+ "bos_token_id": 0,
20
+ "conv1d_width": 4,
21
+ "embeddings_scale_by_sqrt_dim": true,
22
+ "eos_token_id": 0,
23
+ "final_w_init_variance_scale": 0.25,
24
+ "head_dim": 128,
25
+ "hidden_activation": "silu",
26
+ "hidden_size": 1024,
27
+ "intermediate_size": 6144,
28
+ "logits_soft_cap": 30.0,
29
+ "lru_width": 1024,
30
+ "model_type": "recurrent_gemma",
31
+ "num_attention_heads": 8,
32
+ "num_hidden_layers": 8,
33
+ "num_key_value_heads": 2,
34
+ "pad_token_id": 0,
35
+ "partial_rotary_factor": 0.5,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_theta": 10000.0,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.40.1",
40
+ "use_cache": true,
41
+ "vocab_size": 65024,
42
+ "w_init_variance_scale": 0.01
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:726ff00c2f9464283ba0955ebacd54910f2289fbb0e4b696aa304f5bfe6d2bba
3
+ size 671684224
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<EOT>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<EOT>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<EOT>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<EOT>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<META>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<META_START>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<META_END>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<SOS>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<EOT>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "eos_token": "<EOT>",
48
+ "model_max_length": 200000,
49
+ "tokenizer_class": "GPT2Tokenizer",
50
+ "unk_token": "<EOT>"
51
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26980f53a3e0b03ea45ea1f4bf9e9b76c425f4f7ccd38e2db70617697c396ff9
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff