jukofyork commited on
Commit
01ee389
·
verified ·
1 Parent(s): dc05fd8

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DeepSeek-V3-0324-DRAFT-0.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 163840,
14
+ "max_window_layers": 21,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 1,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "factor": 4.0,
23
+ "original_max_position_embeddings": 32768,
24
+ "type": "yarn"
25
+ },
26
+ "rope_theta": 1000000.0,
27
+ "sliding_window": null,
28
+ "tie_word_embeddings": false,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.46.1",
31
+ "use_cache": true,
32
+ "use_sliding_window": false,
33
+ "vocab_size": 129280
34
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.46.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074906b8bd98a96c268fa22160139d3081bef06d779ebb2e368a8dcf6dad78a8
3
+ size 1001284744
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end▁of▁sentence|>",
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
The diff for this file is too large to render. See raw diff