Commit
•
72201cc
1
Parent(s):
e8d1cee
Training in progress, step 500
Browse files- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- added_tokens.json +7 -0
- merges.txt +0 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.json +0 -0
adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "codeparrot/codeparrot-small",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 64,
|
11 |
+
"lora_dropout": 0.4,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"c_attn"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9442a3765a6e6a0fdf1e3e607e4cf00ee0d43d98907dfeadb9ca6764552c1b21
|
3 |
+
size 1188025
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<ASSISTANT_TASK:>": 32771,
|
3 |
+
"<END_TASK>": 32772,
|
4 |
+
"<PAD>": 32768,
|
5 |
+
"<SYSTEM_TASK:>": 32769,
|
6 |
+
"<USER_TASK:>": 32770
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<SYSTEM_TASK:>",
|
4 |
+
"<USER_TASK:>",
|
5 |
+
"<ASSISTANT_TASK:>",
|
6 |
+
"<END_TASK>"
|
7 |
+
],
|
8 |
+
"bos_token": "<|endoftext|>",
|
9 |
+
"eos_token": "<|endoftext|>",
|
10 |
+
"pad_token": "<|endoftext|>",
|
11 |
+
"unk_token": "<|endoftext|>"
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<SYSTEM_TASK:>",
|
5 |
+
"<USER_TASK:>",
|
6 |
+
"<ASSISTANT_TASK:>",
|
7 |
+
"<END_TASK>"
|
8 |
+
],
|
9 |
+
"bos_token": "<|endoftext|>",
|
10 |
+
"clean_up_tokenization_spaces": true,
|
11 |
+
"eos_token": "<|endoftext|>",
|
12 |
+
"model_max_length": 1024,
|
13 |
+
"pad_token": "<PAD>",
|
14 |
+
"tokenizer_class": "GPT2Tokenizer",
|
15 |
+
"unk_token": "<|endoftext|>"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f463c9cb084cf9caf6bb6d50b423e0adc4cb83a097fb01e7adf9b554c010eaaa
|
3 |
+
size 3963
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|