Delete config.json
Browse files- config.json +0 -31
config.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/scratch/project_462000319/general-tools/viking_v2_checkpoints/viking_v2_13B_iter_0476837_bfloat16/",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 1,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
-
"hidden_act": "silu",
|
| 11 |
-
"hidden_size": 5120,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 13824,
|
| 14 |
-
"max_position_embeddings": 4096,
|
| 15 |
-
"max_sequence_length": 4096,
|
| 16 |
-
"model_type": "llama",
|
| 17 |
-
"num_attention_heads": 40,
|
| 18 |
-
"num_hidden_layers": 40,
|
| 19 |
-
"num_key_value_heads": 40,
|
| 20 |
-
"pad_token_id": -1,
|
| 21 |
-
"pretraining_tp": 1,
|
| 22 |
-
"rms_norm_eps": 1e-05,
|
| 23 |
-
"rope_scaling": null,
|
| 24 |
-
"rope_theta": 10000.0,
|
| 25 |
-
"tie_word_embeddings": false,
|
| 26 |
-
"torch_dtype": "bfloat16",
|
| 27 |
-
"transformers_version": "4.40.0",
|
| 28 |
-
"untie_embeddings_and_output_weights": true,
|
| 29 |
-
"use_cache": true,
|
| 30 |
-
"vocab_size": 131072
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|