Upload LLMForSequenceRegression
Browse files- config.json +33 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/nz/OpenRLHF/examples/ckpt/pythia-70m-deduped-rm-harmless",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LLMForSequenceRegression"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": 0.1,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2048,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 2048,
|
| 17 |
+
"mean": 1.366417407989502,
|
| 18 |
+
"model_type": "gpt_neox",
|
| 19 |
+
"normalize_reward": false,
|
| 20 |
+
"num_attention_heads": 8,
|
| 21 |
+
"num_hidden_layers": 6,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rotary_emb_base": 10000,
|
| 25 |
+
"rotary_pct": 0.25,
|
| 26 |
+
"std": 7.083596706390381,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.36.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"use_parallel_residual": true,
|
| 32 |
+
"vocab_size": 50304
|
| 33 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f9286122bb723d9e34a14bce82a1f73aaaca01d34bb79277bcef4ccc1c28952
|
| 3 |
+
size 89351576
|