TheREZOR commited on
Commit
761e44e
·
verified ·
1 Parent(s): 7ed56bd

TinyTalk 2: 8M chat fine-tune (cardputer_ai v2.0)

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPTNeoForCausalLM"
5
+ ],
6
+ "attention_dropout": 0,
7
+ "attention_layers": [
8
+ "global",
9
+ "local",
10
+ "global",
11
+ "local",
12
+ "global",
13
+ "local",
14
+ "global",
15
+ "local"
16
+ ],
17
+ "attention_types": [
18
+ [
19
+ [
20
+ "global",
21
+ "local"
22
+ ],
23
+ 4
24
+ ]
25
+ ],
26
+ "bos_token_id": 50256,
27
+ "classifier_dropout": 0.1,
28
+ "dtype": "float32",
29
+ "embed_dropout": 0,
30
+ "eos_token_id": 50256,
31
+ "gradient_checkpointing": false,
32
+ "hidden_size": 256,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": null,
35
+ "layer_norm_epsilon": 1e-05,
36
+ "max_position_embeddings": 2048,
37
+ "model_type": "gpt_neo",
38
+ "num_heads": 16,
39
+ "num_layers": 8,
40
+ "pad_token_id": null,
41
+ "resid_dropout": 0,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "tie_word_embeddings": true,
48
+ "transformers_version": "5.11.0",
49
+ "use_cache": true,
50
+ "vocab_size": 50257,
51
+ "window_size": 256
52
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "5.11.0",
6
+ "use_cache": true
7
+ }
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 sha256:40e10ee793e157f09fb94d2926db9aa3f81d42814249f1c1db023b7027f17567
3
+ size 78821312
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 2048,
10
+ "pad_token": null,
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>",
13
+ "chat_template": "{% for m in messages %}{% if m['role'] == 'user' %}User: {{ m['content'] }}\n{% else %}Bot: {{ m['content'] }}<|endoftext|>\n{% endif %}{% endfor %}Bot:"
14
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff