Upload model
Browse files- .gitattributes +1 -0
- README.md +3 -0
- config.json +3 -3
- generation_config.json +6 -0
- model.safetensors +3 -0
.gitattributes
CHANGED
@@ -19,3 +19,4 @@ wandb/run-20210830_131354-2654p8r7/logs/debug-internal.log filter=lfs diff=lfs m
|
|
19 |
wandb/run-20210830_131354-2654p8r7/run-2654p8r7.wandb filter=lfs diff=lfs merge=lfs -text
|
20 |
log/debug_0.log filter=lfs diff=lfs merge=lfs -text
|
21 |
wandb/run-20210830_131354-2654p8r7/files/output.log filter=lfs diff=lfs merge=lfs -text
|
|
|
|
19 |
wandb/run-20210830_131354-2654p8r7/run-2654p8r7.wandb filter=lfs diff=lfs merge=lfs -text
|
20 |
log/debug_0.log filter=lfs diff=lfs merge=lfs -text
|
21 |
wandb/run-20210830_131354-2654p8r7/files/output.log filter=lfs diff=lfs merge=lfs -text
|
22 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,6 @@
|
|
|
|
|
|
|
|
1 |
# CodeParrot
|
2 |
|
3 |
CodeParrot (small) is a 110M parameter GPT-2 model trained on the [CodeParrot Python code dataset](https://huggingface.co/datasets/transformersbook/codeparrot). The model is trained in Chapter 10: Training Transformers from Scratch in the [NLP with Transformers book](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/). You can find the full code in the accompanying [Github repository](https://github.com/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb).
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
# CodeParrot
|
5 |
|
6 |
CodeParrot (small) is a 110M parameter GPT-2 model trained on the [CodeParrot Python code dataset](https://huggingface.co/datasets/transformersbook/codeparrot). The model is trained in Chapter 10: Training Transformers from Scratch in the [NLP with Transformers book](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/). You can find the full code in the accompanying [Github repository](https://github.com/nlp-with-transformers/notebooks/blob/main/10_transformers-from-scratch.ipynb).
|
config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "./",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
@@ -8,7 +7,6 @@
|
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
11 |
-
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"model_type": "gpt2",
|
@@ -18,7 +16,9 @@
|
|
18 |
"n_inner": null,
|
19 |
"n_layer": 12,
|
20 |
"n_positions": 1024,
|
|
|
21 |
"resid_pdrop": 0.1,
|
|
|
22 |
"scale_attn_weights": true,
|
23 |
"summary_activation": null,
|
24 |
"summary_first_dropout": 0.1,
|
@@ -32,7 +32,7 @@
|
|
32 |
}
|
33 |
},
|
34 |
"torch_dtype": "float32",
|
35 |
-
"transformers_version": "4.
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 32768
|
38 |
}
|
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
|
|
7 |
"bos_token_id": 50256,
|
8 |
"embd_pdrop": 0.1,
|
9 |
"eos_token_id": 50256,
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
"model_type": "gpt2",
|
|
|
16 |
"n_inner": null,
|
17 |
"n_layer": 12,
|
18 |
"n_positions": 1024,
|
19 |
+
"reorder_and_upcast_attn": false,
|
20 |
"resid_pdrop": 0.1,
|
21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
22 |
"scale_attn_weights": true,
|
23 |
"summary_activation": null,
|
24 |
"summary_first_dropout": 0.1,
|
|
|
32 |
}
|
33 |
},
|
34 |
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.55.4",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 32768
|
38 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.55.4"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff75bb3b15a8a5bc38283ffecae0e6425f35b176ee9a4c45e2e92847dd60f9bd
|
3 |
+
size 444048000
|