monsoon-nlp commited on
Commit
90d1148
1 Parent(s): c1efa8a
README.md CHANGED
@@ -1,3 +1,17 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-step-50K-105b
4
+ datasets:
5
+ - cerebras/SlimPajama-627B
6
+ - bigcode/starcoderdata
7
+ - monsoon-nlp/greenbeing-proteins
8
+ language:
9
+ - en
10
  ---
11
+
12
+ # tinyllama-proteinpretrain-quinoa
13
+
14
+ Continued pretraining of TinyLLaMA-1.1B on the "research" split (quinoa
15
+ protein sequences) of GreenBeing-Proteins dataset.
16
+
17
+ More details TBD
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 22,
18
+ "num_key_value_heads": 4,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.40.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.40.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65443ebfaf482170d04c8145faf0e0e08cb05cc56479d1ab12f12fc793b458e0
3
+ size 4400216536
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "</s>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df827ee6f41b60c032fc1e942ede93b6517d7dcdcae49eeab71e7c8fc17f6d0a
3
+ size 4920