Upload RWForCausalLM
Browse files- config.json +29 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/trained-model-1-merged",
|
| 3 |
+
"alibi": true,
|
| 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 |
+
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
|
| 12 |
+
},
|
| 13 |
+
"bias": true,
|
| 14 |
+
"bos_token_id": 1,
|
| 15 |
+
"eos_token_id": 2,
|
| 16 |
+
"hidden_dropout": 0.0,
|
| 17 |
+
"hidden_size": 2048,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"layer_norm_epsilon": 1e-05,
|
| 20 |
+
"model_type": "RefinedWebModel",
|
| 21 |
+
"multi_query": false,
|
| 22 |
+
"n_head": 32,
|
| 23 |
+
"n_layer": 24,
|
| 24 |
+
"parallel_attn": false,
|
| 25 |
+
"torch_dtype": "float16",
|
| 26 |
+
"transformers_version": "4.30.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50304
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.30.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a3069203eebb46d884d74d9dc50ca277de21d788708d444c324d5d540e87134
|
| 3 |
+
size 2623348889
|