Hugging Face's logo

Delcos
/
Velara-11B-v3

Text Generation
Transformers
Safetensors
English
llama
starling
mistral
llama-2
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Delcos commited on
Commit
a22f2df
•
1 Parent(s): 520bc78

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +29 -29
config.json CHANGED
@@ -1,29 +1,29 @@
1
- {
2
- "_name_or_path": "Delcos/Velara-11B-V2",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 4096,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 32,
18
- "num_hidden_layers": 48,
19
- "num_key_value_heads": 8,
20
- "pretraining_tp": 1,
21
- "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
23
- "rope_theta": 500000.0,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.41.0",
27
- "use_cache": false,
28
- "vocab_size": 128256
29
- }
 
1
+ {
2
+ "_name_or_path": "Delcos/Velara-11B-v3",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 48,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.41.0",
27
+ "use_cache": false,
28
+ "vocab_size": 128256
29
+ }