Commit
•
fe5151f
1
Parent(s):
063674f
Upload GPTNeoXForCausalLM
Browse files- config.json +26 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "togethercomputer/RedPajama-INCITE-Instruct-3B-v1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": 0.1,
|
| 8 |
+
"eos_token_id": 0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_size": 2560,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 10240,
|
| 13 |
+
"layer_norm_eps": 1e-05,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "gpt_neox",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"rotary_emb_base": 10000,
|
| 19 |
+
"rotary_pct": 1.0,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "bfloat16",
|
| 22 |
+
"transformers_version": "4.29.0.dev0",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"use_parallel_residual": false,
|
| 25 |
+
"vocab_size": 50432
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.29.0.dev0"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23ff4b07d29e422d8a8491489e4c8e1e33d1dd73a2fac240da38f5060c6ea1a1
|
| 3 |
+
size 5686113497
|