ghosthets commited on
Commit
ce3668f
·
verified ·
1 Parent(s): db8321a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "ci",
3
+ "architectures": [
4
+ "CiModelForCausalLM"
5
+ ],
6
+ "hidden_size": 1024,
7
+ "num_hidden_layers": 16,
8
+ "num_attention_heads": 16,
9
+ "num_key_value_heads": 8,
10
+ "intermediate_size": 2816,
11
+ "vocab_size": 32000,
12
+ "max_position_embeddings": 512,
13
+ "hidden_dropout_prob": 0.05,
14
+ "rms_norm_eps": 1e-06,
15
+ "tie_word_embeddings": true,
16
+ "torch_dtype": "float16",
17
+ "transformers_version": "4.40.0",
18
+ "use_emotion": true,
19
+ "emotion_dim": 512,
20
+ "num_emotions": 12,
21
+ "use_persona": true,
22
+ "persona_dim": 768,
23
+ "use_tools": true,
24
+ "num_tool_types": 8,
25
+ "tool_embed_dim": 512,
26
+ "use_reasoning": true,
27
+ "reasoning_dim": 768,
28
+ "reasoning_steps": 3,
29
+ "use_kan": true,
30
+ "kan_grid_size": 5,
31
+ "use_snn": true,
32
+ "snn_layers": [
33
+ 3,
34
+ 7,
35
+ 11,
36
+ 15
37
+ ],
38
+ "use_moe": true,
39
+ "num_experts": 8,
40
+ "num_selected_experts": 2,
41
+ "training_step": 74000
42
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "temperature": 0.7,
4
+ "top_k": 50,
5
+ "top_p": 0.9,
6
+ "repetition_penalty": 1.1,
7
+ "max_length": 512,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "pad_token_id": 0
11
+ }
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 sha256:7903f4383cb874e9d6e63e182fa3363293697b309d7502cc0927513178848222
3
+ size 2302731440
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "</s>",
7
+ "cls_token": "<s>",
8
+ "mask_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>",
5
+ "pad_token": "<pad>",
6
+ "cls_token": "<s>",
7
+ "sep_token": "</s>",
8
+ "mask_token": "<unk>",
9
+ "model_max_length": 512,
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "added_tokens_decoder": {
12
+ "0": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "normalized": false
18
+ },
19
+ "1": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "single_word": false,
24
+ "normalized": false
25
+ },
26
+ "2": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "single_word": false,
31
+ "normalized": false
32
+ },
33
+ "3": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "rstrip": false,
37
+ "single_word": false,
38
+ "normalized": false
39
+ }
40
+ }
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff