Upload config.json with huggingface_hub
Browse files- config.json +34 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/scratch/output_models/test020-20k/checkpoint-2000",
|
| 3 |
+
"alibi": false,
|
| 4 |
+
"apply_residual_connection_post_layernorm": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"RWForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auto_map": {
|
| 10 |
+
"AutoConfig": "configuration_RW.RWConfig",
|
| 11 |
+
"AutoModel": "modelling_RW.RWModel",
|
| 12 |
+
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM",
|
| 13 |
+
"AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
|
| 14 |
+
"AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
|
| 15 |
+
"AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"
|
| 16 |
+
},
|
| 17 |
+
"bias": false,
|
| 18 |
+
"bos_token_id": 11,
|
| 19 |
+
"eos_token_id": 11,
|
| 20 |
+
"hidden_dropout": 0.0,
|
| 21 |
+
"hidden_size": 8192,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"layer_norm_epsilon": 1e-05,
|
| 24 |
+
"model_type": "RefinedWeb",
|
| 25 |
+
"n_head": 128,
|
| 26 |
+
"n_head_kv": 8,
|
| 27 |
+
"n_layer": 60,
|
| 28 |
+
"parallel_attn": true,
|
| 29 |
+
"torch_dtype": "float16",
|
| 30 |
+
"transformers_version": "4.31.0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"rope_theta": 1000000,
|
| 33 |
+
"vocab_size": 65040
|
| 34 |
+
}
|