facebook-llama
commited on
Commit
•
48a7648
1
Parent(s):
e60a87d
Upload model
Browse files- config.json +16 -19
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"attn_pdrop": 0.
|
8 |
-
"bos_token_id":
|
9 |
-
"embd_pdrop": 0.
|
10 |
"eos_token_id": 50256,
|
11 |
-
"gradient_checkpointing": false,
|
12 |
"initializer_range": 0.02,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
-
"model_type": "
|
15 |
-
"n_ctx":
|
16 |
-
"n_embd":
|
17 |
-
"n_head":
|
18 |
"n_inner": null,
|
19 |
-
"n_layer":
|
20 |
-
"n_positions":
|
21 |
-
"
|
22 |
-
"
|
|
|
23 |
"scale_attn_weights": true,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
@@ -29,14 +29,11 @@
|
|
29 |
"task_specific_params": {
|
30 |
"text-generation": {
|
31 |
"do_sample": true,
|
32 |
-
"max_length": 50
|
33 |
-
"temperature": 1.0
|
34 |
}
|
35 |
},
|
36 |
-
"tie_word_embeddings": false,
|
37 |
-
"tokenizer_class": "GPT2Tokenizer",
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.39.0",
|
40 |
"use_cache": true,
|
41 |
-
"vocab_size":
|
42 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "codeparrot/codeparrot-small",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
"eos_token_id": 50256,
|
|
|
11 |
"initializer_range": 0.02,
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": true,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": true,
|
23 |
"scale_attn_weights": true,
|
24 |
"summary_activation": null,
|
25 |
"summary_first_dropout": 0.1,
|
|
|
29 |
"task_specific_params": {
|
30 |
"text-generation": {
|
31 |
"do_sample": true,
|
32 |
+
"max_length": 50
|
|
|
33 |
}
|
34 |
},
|
|
|
|
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.39.0",
|
37 |
"use_cache": true,
|
38 |
+
"vocab_size": 32768
|
39 |
}
|
generation_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
"eos_token_id": 50256,
|
5 |
"transformers_version": "4.39.0"
|
6 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
"eos_token_id": 50256,
|
5 |
"transformers_version": "4.39.0"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:404bb13ed090092f634cc0b6c07da88a647e23149a6307d76ad513cb41fa436d
|
3 |
+
size 444048000
|