Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 49152
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "WizardLM/WizardCoder-1B-V1.0",
|
3 |
+
"activation_function": "gelu_pytorch_tanh",
|
4 |
+
"architectures": [
|
5 |
+
"GPTBigCodeForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_softmax_in_fp32": true,
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 0,
|
12 |
+
"inference_runner": 0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"layer_norm_epsilon": 1e-05,
|
15 |
+
"max_batch_size": null,
|
16 |
+
"max_sequence_length": null,
|
17 |
+
"model_type": "gpt_bigcode",
|
18 |
+
"multi_query": true,
|
19 |
+
"n_embd": 2048,
|
20 |
+
"n_head": 16,
|
21 |
+
"n_inner": 8192,
|
22 |
+
"n_layer": 24,
|
23 |
+
"n_positions": 8192,
|
24 |
+
"pad_key_length": true,
|
25 |
+
"pre_allocate_kv_cache": false,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"scale_attention_softmax_in_fp32": true,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"summary_activation": null,
|
30 |
+
"summary_first_dropout": 0.1,
|
31 |
+
"summary_proj_to_labels": true,
|
32 |
+
"summary_type": "cls_index",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"torch_dtype": "float16",
|
35 |
+
"transformers_version": "4.32.1",
|
36 |
+
"use_cache": false,
|
37 |
+
"validate_runner_input": true,
|
38 |
+
"vocab_size": 49153
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"transformers_version": "4.32.1"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9634353d3d1e127a827808ae09f203bb845077da41919b568210abbe36424b82
|
3 |
+
size 2274513885
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<fim_prefix>",
|
5 |
+
"<fim_middle>",
|
6 |
+
"<fim_suffix>",
|
7 |
+
"<fim_pad>",
|
8 |
+
"<filename>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<issue_start>",
|
11 |
+
"<issue_comment>",
|
12 |
+
"<issue_closed>",
|
13 |
+
"<jupyter_start>",
|
14 |
+
"<jupyter_text>",
|
15 |
+
"<jupyter_code>",
|
16 |
+
"<jupyter_output>",
|
17 |
+
"<empty_output>",
|
18 |
+
"<commit_before>",
|
19 |
+
"<commit_msg>",
|
20 |
+
"<commit_after>",
|
21 |
+
"<reponame>"
|
22 |
+
],
|
23 |
+
"bos_token": "<|endoftext|>",
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"pad_token": "[PAD]",
|
26 |
+
"unk_token": "<|endoftext|>"
|
27 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<|endoftext|>",
|
5 |
+
"<fim_prefix>",
|
6 |
+
"<fim_middle>",
|
7 |
+
"<fim_suffix>",
|
8 |
+
"<fim_pad>",
|
9 |
+
"<filename>",
|
10 |
+
"<gh_stars>",
|
11 |
+
"<issue_start>",
|
12 |
+
"<issue_comment>",
|
13 |
+
"<issue_closed>",
|
14 |
+
"<jupyter_start>",
|
15 |
+
"<jupyter_text>",
|
16 |
+
"<jupyter_code>",
|
17 |
+
"<jupyter_output>",
|
18 |
+
"<empty_output>",
|
19 |
+
"<commit_before>",
|
20 |
+
"<commit_msg>",
|
21 |
+
"<commit_after>",
|
22 |
+
"<reponame>"
|
23 |
+
],
|
24 |
+
"bos_token": "<|endoftext|>",
|
25 |
+
"clean_up_tokenization_spaces": true,
|
26 |
+
"eos_token": "<|endoftext|>",
|
27 |
+
"model_max_length": 8192,
|
28 |
+
"padding_side": "right",
|
29 |
+
"tokenizer_class": "GPT2Tokenizer",
|
30 |
+
"unk_token": "<|endoftext|>",
|
31 |
+
"vocab_size": 49152
|
32 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|