Ahmetemiiii2 commited on
Commit
5a5ffc9
·
verified ·
1 Parent(s): 3e045c3

Töz-1 (w_029999.pt)

Browse files
README.md ADDED
File without changes
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float16",
9
+ "eos_token_id": 0,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_types": [
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention"
34
+ ],
35
+ "max_position_embeddings": 1024,
36
+ "max_window_layers": 28,
37
+ "model_type": "qwen3",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 18,
40
+ "num_key_value_heads": 12,
41
+ "pad_token_id": 0,
42
+ "rms_norm_eps": 1e-06,
43
+ "rope_parameters": {
44
+ "rope_theta": 10000.0,
45
+ "rope_type": "default"
46
+ },
47
+ "sliding_window": null,
48
+ "tie_word_embeddings": true,
49
+ "transformers_version": "5.2.0",
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 32768,
53
+ "rope_theta": 10000.0,
54
+ "rope_scaling": null,
55
+ "torch_dtype": "float16"
56
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "do_sample": true,
4
+ "eos_token_id": 0,
5
+ "max_new_tokens": 128,
6
+ "pad_token_id": 0,
7
+ "repetition_penalty": 1.1,
8
+ "temperature": 0.8,
9
+ "top_p": 0.95,
10
+ "transformers_version": "5.2.0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b94a16d1353d6643173520e88be78aea3a6c4aa08ee89f77ecec1aa682a1fc
3
+ size 390153808
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": false,
3
+ "eos_token": "<|endoftext|>",
4
+ "model_input_names": [
5
+ "input_ids",
6
+ "attention_mask"
7
+ ],
8
+ "model_max_length": 1024,
9
+ "pad_token": "<|endoftext|>",
10
+ "tokenizer_class": "PreTrainedTokenizerFast"
11
+ }