Training in progress, step 10
Browse files- config.json +37 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigcode/santacoder",
|
3 |
+
"activation_function": "gelu_fast",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadCustomModel"
|
6 |
+
],
|
7 |
+
"attention_head_type": "multiquery",
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "bigcode/santacoder--configuration_gpt2_mq.GPT2CustomConfig",
|
11 |
+
"AutoModelForCausalLM": "bigcode/santacoder--modeling_gpt2_mq.GPT2LMHeadCustomModel"
|
12 |
+
},
|
13 |
+
"bos_token_id": 49152,
|
14 |
+
"embd_pdrop": 0.1,
|
15 |
+
"eos_token_id": 49152,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"layer_norm_epsilon": 1e-05,
|
18 |
+
"model_type": "gpt2",
|
19 |
+
"n_embd": 2048,
|
20 |
+
"n_head": 16,
|
21 |
+
"n_inner": 8192,
|
22 |
+
"n_layer": 24,
|
23 |
+
"n_positions": 2048,
|
24 |
+
"reorder_and_upcast_attn": false,
|
25 |
+
"resid_pdrop": 0.1,
|
26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
27 |
+
"scale_attn_weights": true,
|
28 |
+
"summary_activation": null,
|
29 |
+
"summary_first_dropout": 0.1,
|
30 |
+
"summary_proj_to_labels": true,
|
31 |
+
"summary_type": "cls_index",
|
32 |
+
"summary_use_proj": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.33.2",
|
35 |
+
"use_cache": false,
|
36 |
+
"vocab_size": 49280
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b2f3ac91a3e171f40fd69dff17d7d64476cdeff3150039611159ef881480eea
|
3 |
+
size 4600336581
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb654d17139a6aa5931b511ee1878f9425543b8d87babfd7a8d97ccb0c7bf680
|
3 |
+
size 4027
|