Montalte commited on
Commit
071be0c
·
verified ·
1 Parent(s): 5e480a7

Upload folder using huggingface_hub

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {{ '<|endoftext|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>
2
+ ' + content + '<|assistant|>
3
+ ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' }}{% endif %}{% endfor %}
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Olmo3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 100257,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "layer_types": [
15
+ "sliding_attention",
16
+ "sliding_attention",
17
+ "sliding_attention",
18
+ "full_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "full_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "full_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "full_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention"
47
+ ],
48
+ "max_position_embeddings": 65536,
49
+ "model_type": "olmo3",
50
+ "num_attention_heads": 32,
51
+ "num_hidden_layers": 32,
52
+ "num_key_value_heads": 32,
53
+ "pad_token_id": 100277,
54
+ "rms_norm_eps": 1e-06,
55
+ "rope_parameters": {
56
+ "attention_factor": 1.2079441541679836,
57
+ "beta_fast": 32,
58
+ "beta_slow": 1,
59
+ "factor": 8.0,
60
+ "original_max_position_embeddings": 8192,
61
+ "rope_theta": 500000,
62
+ "rope_type": "yarn"
63
+ },
64
+ "sliding_window": 4096,
65
+ "tie_word_embeddings": false,
66
+ "transformers_version": "5.3.0",
67
+ "use_cache": true,
68
+ "vocab_size": 100278
69
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "5.3.0"
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8412d34424b240cbf6a4a995344ba577392e50ed8cdff1f7b935226b53949d
3
+ size 14596063960
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "model_max_length": 65536,
10
+ "pad_token": "<|pad|>",
11
+ "padding_side": "left",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "TokenizersBackend",
14
+ "unk_token": "<|endoftext|>"
15
+ }