Upload folder using huggingface_hub
Browse files- config.json +16 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- training_metrics.json +11 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SnowflakeCoreG1"
|
4 |
+
],
|
5 |
+
"model_type": "snowflake_core",
|
6 |
+
"vocab_size": 50257,
|
7 |
+
"embed_dim": 1024,
|
8 |
+
"num_heads": 16,
|
9 |
+
"num_layers": 24,
|
10 |
+
"max_length": 2048,
|
11 |
+
"ffn_dim": 4096,
|
12 |
+
"pad_token_id": 50256,
|
13 |
+
"eos_token_id": 50256,
|
14 |
+
"bos_token_id": 50256,
|
15 |
+
"unk_token_id": 50256
|
16 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_sample": true,
|
3 |
+
"temperature": 0.8,
|
4 |
+
"top_p": 0.9,
|
5 |
+
"max_new_tokens": 100
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2bed57f3fe592425e4ed734949524b7f4dc5b471b9a2ec3f74d4c3ab2a08ad
|
3 |
+
size 1629367568
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f88c4f13cc0f354ba2920a0b67cbd2b07834e67190b0cca3283d3b4d4a505397
|
3 |
+
size 1629446071
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"clean_up_tokenization_spaces": false,
|
15 |
+
"eos_token": "<|endoftext|>",
|
16 |
+
"extra_special_tokens": {},
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
training_metrics.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epochs_completed": 0,
|
3 |
+
"best_validation_loss": Infinity,
|
4 |
+
"final_train_loss": null,
|
5 |
+
"final_validation_loss": null,
|
6 |
+
"training_history": {
|
7 |
+
"train_losses": [],
|
8 |
+
"val_losses": [],
|
9 |
+
"val_perplexities": []
|
10 |
+
}
|
11 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|