Commit
•
71de503
1
Parent(s):
dec872c
RLHF model of StarCoder
Browse files- README.md +5 -0
- pytorch_model.bin +1 -1
- tokenizer_config.json +0 -8
README.md
CHANGED
@@ -3,6 +3,8 @@ license: bigcode-openrail-m
|
|
3 |
base_model: bigcode/tiny_starcoder_py
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: tinystarcoder-rlhf-model
|
8 |
results: []
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# tinystarcoder-rlhf-model
|
15 |
|
16 |
This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py) on the None dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: bigcode/tiny_starcoder_py
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
model-index:
|
9 |
- name: tinystarcoder-rlhf-model
|
10 |
results: []
|
|
|
16 |
# tinystarcoder-rlhf-model
|
17 |
|
18 |
This model is a fine-tuned version of [bigcode/tiny_starcoder_py](https://huggingface.co/bigcode/tiny_starcoder_py) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6931
|
21 |
+
- Accuracy: 0.0
|
22 |
|
23 |
## Model description
|
24 |
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 656652573
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e0724433c3fd05e3d29d70c6b9628301756eb170194225ce7b6bca14b4415a7
|
3 |
size 656652573
|
tokenizer_config.json
CHANGED
@@ -24,16 +24,8 @@
|
|
24 |
"bos_token": "<|endoftext|>",
|
25 |
"clean_up_tokenization_spaces": true,
|
26 |
"eos_token": "<|endoftext|>",
|
27 |
-
"max_length": 256,
|
28 |
"model_max_length": 1000000000000000019884624838656,
|
29 |
-
"pad_to_multiple_of": null,
|
30 |
-
"pad_token": "[PAD]",
|
31 |
-
"pad_token_type_id": 0,
|
32 |
-
"padding_side": "right",
|
33 |
-
"stride": 0,
|
34 |
"tokenizer_class": "GPT2Tokenizer",
|
35 |
-
"truncation_side": "right",
|
36 |
-
"truncation_strategy": "longest_first",
|
37 |
"unk_token": "<|endoftext|>",
|
38 |
"vocab_size": 49152
|
39 |
}
|
|
|
24 |
"bos_token": "<|endoftext|>",
|
25 |
"clean_up_tokenization_spaces": true,
|
26 |
"eos_token": "<|endoftext|>",
|
|
|
27 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
|
|
|
|
28 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
29 |
"unk_token": "<|endoftext|>",
|
30 |
"vocab_size": 49152
|
31 |
}
|