Text Generation
Transformers
PyTorch
Safetensors
English
hf_olmo
custom_code
shanearora commited on
Commit
643a150
1 Parent(s): e308a16

Delete temp.json

Browse files
Files changed (1) hide show
  1. temp.json +0 -51
temp.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "activation_type": "swiglu",
3
- "alibi": false,
4
- "alibi_bias_max": 8.0,
5
- "architectures": [
6
- "OLMoForCausalLM"
7
- ],
8
- "attention_dropout": 0.0,
9
- "attention_layer_norm": false,
10
- "attention_layer_norm_with_affine": false,
11
- "bias_for_layer_norm": false,
12
- "block_group_size": 1,
13
- "block_type": "sequential",
14
- "d_model": 2048,
15
- "embedding_dropout": 0.0,
16
- "embedding_size": 50304,
17
- "eos_token_id": 50279,
18
- "flash_attention": false,
19
- "include_bias": false,
20
- "init_cutoff_factor": null,
21
- "init_device": "meta",
22
- "init_fn": "mitchell",
23
- "init_std": 0.02,
24
- "layer_norm_type": "default",
25
- "layer_norm_with_affine": false,
26
- "max_sequence_length": 2048,
27
- "mlp_hidden_size": null,
28
- "mlp_ratio": 8,
29
- "model_type": "hf_olmo",
30
- "multi_query_attention": false,
31
- "n_heads": 16,
32
- "n_layers": 16,
33
- "pad_token_id": 1,
34
- "precision": "amp_bf16",
35
- "residual_dropout": 0.0,
36
- "rope": true,
37
- "rope_full_precision": true,
38
- "scale_logits": false,
39
- "transformers_version": "4.37.1",
40
- "use_cache": true,
41
- "vocab_size": 50280,
42
- "weight_tying": true,
43
- "auto_map": {
44
- "AutoConfig": "configuration_olmo.OLMoConfig",
45
- "AutoModelForCausalLM": "modeling_olmo.OLMoForCausalLM",
46
- "AutoTokenizer": [
47
- "tokenization_olmo_fast.OLMoTokenizerFast",
48
- "tokenization_olmo_fast.OLMoTokenizerFast"
49
- ]
50
- }
51
- }