Delete config.json
Browse files- config.json +0 -25
config.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/fsx/ckpts/7b_tok=neox_data=pilev2-recontam_lower-code_bs=8m_tp=4_pp=1_init=wang-small-init/global_step69000_hf",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"GPTNeoXForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 0,
|
| 7 |
-
"eos_token_id": 0,
|
| 8 |
-
"hidden_act": "gelu",
|
| 9 |
-
"hidden_size": 6144,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"intermediate_size": 24576,
|
| 12 |
-
"layer_norm_eps": 1e-05,
|
| 13 |
-
"max_position_embeddings": 4096,
|
| 14 |
-
"model_type": "gpt_neox",
|
| 15 |
-
"num_attention_heads": 48,
|
| 16 |
-
"num_hidden_layers": 16,
|
| 17 |
-
"rotary_emb_base": 10000,
|
| 18 |
-
"rotary_pct": 0.25,
|
| 19 |
-
"tie_word_embeddings": false,
|
| 20 |
-
"torch_dtype": "float16",
|
| 21 |
-
"transformers_version": "4.27.4",
|
| 22 |
-
"use_cache": true,
|
| 23 |
-
"use_parallel_residual": true,
|
| 24 |
-
"vocab_size": 50432
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|