Hugging Face's logo

hf-internal-testing
/
olmo-hybrid

Safetensors
olmo_hybrid
Model card Files
xet
Community
AntonV HF Staff commited on
Commit
b25261b
·
verified ·
1 Parent(s): 559eddd

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. chat_template.jinja +4 -0
  2. config.json +80 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +11 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +13 -0
  9. vocab.json +0 -0
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 100257,
9
+ "fla_hybrid_attention_indices": [
10
+ 3,
11
+ 7,
12
+ 11,
13
+ 15,
14
+ 19,
15
+ 23,
16
+ 27,
17
+ 31
18
+ ],
19
+ "hidden_act": "silu",
20
+ "hidden_size": 3840,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 11008,
23
+ "layer_types": [
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention"
56
+ ],
57
+ "linear_allow_neg_eigval": true,
58
+ "linear_conv_kernel_dim": 4,
59
+ "linear_key_head_dim": 96,
60
+ "linear_num_key_heads": 30,
61
+ "linear_num_value_heads": 30,
62
+ "linear_use_gate": true,
63
+ "linear_value_head_dim": 192,
64
+ "max_position_embeddings": 8192,
65
+ "model_type": "olmo3_2_hybrid",
66
+ "num_attention_heads": 30,
67
+ "num_hidden_layers": 32,
68
+ "num_key_value_heads": 30,
69
+ "pad_token_id": 100277,
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_parameters": {
72
+ "rope_theta": 500000,
73
+ "rope_type": "default"
74
+ },
75
+ "sliding_window": 4096,
76
+ "tie_word_embeddings": false,
77
+ "transformers_version": "5.0.0.dev0",
78
+ "use_cache": true,
79
+ "vocab_size": 100278
80
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 100257,
4
+ "pad_token_id": 100277,
5
+ "transformers_version": "5.0.0.dev0"
6
+ }
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 sha256:08e9ba6ad99313ed4b9056d8a7ad21a2a1610b31c3e0ba87b2b7f854e9b2db1a
3
+ size 14860667240
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|pad|>",
4
+ "unk_token": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ }
11
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "model_max_length": 8192,
10
+ "pad_token": "<|pad|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff