k050506koch
commited on
Commit
•
b94615a
1
Parent(s):
2789c02
Delete gpt3-small-fineweb-1M-step-70000
Browse files- gpt3-small-fineweb-1M-step-70000/config.json +0 -33
- gpt3-small-fineweb-1M-step-70000/generation_config.json +0 -6
- gpt3-small-fineweb-1M-step-70000/merges.txt +0 -0
- gpt3-small-fineweb-1M-step-70000/model.safetensors +0 -3
- gpt3-small-fineweb-1M-step-70000/special_tokens_map.json +0 -6
- gpt3-small-fineweb-1M-step-70000/tokenizer.json +0 -0
- gpt3-small-fineweb-1M-step-70000/tokenizer_config.json +0 -20
- gpt3-small-fineweb-1M-step-70000/vocab.json +0 -0
gpt3-small-fineweb-1M-step-70000/config.json
DELETED
@@ -1,33 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"activation_function": "gelu",
|
3 |
-
"architectures": [
|
4 |
-
"CustomGPT2LMHeadModel"
|
5 |
-
],
|
6 |
-
"attn_pdrop": 0.0,
|
7 |
-
"bos_token_id": 50256,
|
8 |
-
"embd_pdrop": 0.0,
|
9 |
-
"eos_token_id": 50256,
|
10 |
-
"initializer_range": 0.02,
|
11 |
-
"layer_norm_epsilon": 1e-05,
|
12 |
-
"model_type": "gpt2",
|
13 |
-
"n_ctx": 1024,
|
14 |
-
"n_embd": 256,
|
15 |
-
"n_head": 4,
|
16 |
-
"n_inner": 1024,
|
17 |
-
"n_layer": 6,
|
18 |
-
"n_positions": 1024,
|
19 |
-
"reorder_and_upcast_attn": false,
|
20 |
-
"resid_pdrop": 0.0,
|
21 |
-
"scale_attn_by_inverse_layer_idx": false,
|
22 |
-
"scale_attn_weights": true,
|
23 |
-
"summary_activation": null,
|
24 |
-
"summary_first_dropout": 0.1,
|
25 |
-
"summary_proj_to_labels": true,
|
26 |
-
"summary_type": "cls_index",
|
27 |
-
"summary_use_proj": true,
|
28 |
-
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.45.2",
|
30 |
-
"use_cache": true,
|
31 |
-
"use_pre_layernorm": true,
|
32 |
-
"vocab_size": 50257
|
33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt3-small-fineweb-1M-step-70000/generation_config.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 50256,
|
4 |
-
"eos_token_id": 50256,
|
5 |
-
"transformers_version": "4.45.2"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt3-small-fineweb-1M-step-70000/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
gpt3-small-fineweb-1M-step-70000/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a2950bb764fc38fcc077ad39462541189b11900259d5906227191e5c1595df32
|
3 |
-
size 71475528
|
|
|
|
|
|
|
|
gpt3-small-fineweb-1M-step-70000/special_tokens_map.json
DELETED
@@ -1,6 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<|endoftext|>",
|
3 |
-
"eos_token": "<|endoftext|>",
|
4 |
-
"pad_token": "<|endoftext|>",
|
5 |
-
"unk_token": "<|endoftext|>"
|
6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt3-small-fineweb-1M-step-70000/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
gpt3-small-fineweb-1M-step-70000/tokenizer_config.json
DELETED
@@ -1,20 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"50256": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
}
|
12 |
-
},
|
13 |
-
"bos_token": "<|endoftext|>",
|
14 |
-
"clean_up_tokenization_spaces": false,
|
15 |
-
"eos_token": "<|endoftext|>",
|
16 |
-
"model_max_length": 1024,
|
17 |
-
"pad_token": "<|endoftext|>",
|
18 |
-
"tokenizer_class": "GPT2Tokenizer",
|
19 |
-
"unk_token": "<|endoftext|>"
|
20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpt3-small-fineweb-1M-step-70000/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|