First ver
Browse files- config.json +27 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTJForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"embd_pdrop": 0.0,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gptj",
|
| 13 |
+
"n_embd": 1024,
|
| 14 |
+
"n_head": 16,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 20,
|
| 17 |
+
"n_positions": 2048,
|
| 18 |
+
"resid_pdrop": 0.0,
|
| 19 |
+
"rotary_dim": 32,
|
| 20 |
+
"scale_attn_weights": true,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.26.0",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 50295
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.26.0",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:983a046a0ba755e726b607375d65a30d09ef8a070f18fc16363f66dfa6aaa87a
|
| 3 |
+
size 1503395425
|