Commit
•
cb12c89
1
Parent(s):
79c9b21
Upload 8 files
Browse files- config.json +39 -0
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/datadrive/disk1/pierpaolo/llm/itlangadapt/bloom-1b7_it",
|
3 |
+
"adapters": {
|
4 |
+
"adapters": {},
|
5 |
+
"config_map": {},
|
6 |
+
"fusion_config_map": {},
|
7 |
+
"fusions": {}
|
8 |
+
},
|
9 |
+
"apply_residual_connection_post_layernorm": false,
|
10 |
+
"architectures": [
|
11 |
+
"BloomForCausalLM"
|
12 |
+
],
|
13 |
+
"attention_dropout": 0.0,
|
14 |
+
"attention_softmax_in_fp32": true,
|
15 |
+
"bias_dropout_fusion": true,
|
16 |
+
"bos_token_id": 1,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"hidden_dropout": 0.0,
|
19 |
+
"hidden_size": 2048,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"layer_norm_epsilon": 1e-05,
|
22 |
+
"masked_softmax_fusion": true,
|
23 |
+
"model_type": "bloom",
|
24 |
+
"n_head": 16,
|
25 |
+
"n_inner": null,
|
26 |
+
"n_layer": 24,
|
27 |
+
"offset_alibi": 100,
|
28 |
+
"pad_token_id": 3,
|
29 |
+
"pretraining_tp": 2,
|
30 |
+
"seq_length": 4096,
|
31 |
+
"skip_bias_add": true,
|
32 |
+
"skip_bias_add_qkv": false,
|
33 |
+
"slow_but_exact": false,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.30.2",
|
36 |
+
"unk_token_id": 0,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 250680
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 3,
|
6 |
+
"transformers_version": "4.30.2"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd6120c48d3fbeedbbcd098cfd087ff08411dae31b926354b38166476f0bf8f
|
3 |
+
size 13776173629
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84758176380e9125120eaa42f506a612abeb1c05fb0b6a89bda3fc2b781b9c57
|
3 |
+
size 6888098489
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1784c9e20ffdc46b706882695c2108245d7626a328b6d70a37d079ad1fbbc989
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f161a384f8fc9e2b53b3403f798d0e517a4802dc69d16bc70f5b3c9531b2371e
|
3 |
+
size 627
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10888bd449a37a9f6fee153724d2e42c9574132f2918e709519d8efec6fee8e1
|
3 |
+
size 3899
|