SykoLLM 233M
Browse files- config.json +22 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SykoCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_size": 768,
|
| 9 |
+
"intermediate_size": 2304,
|
| 10 |
+
"max_position_embeddings": 1024,
|
| 11 |
+
"model_type": "syko",
|
| 12 |
+
"num_attention_heads": 6,
|
| 13 |
+
"num_hidden_layers": 24,
|
| 14 |
+
"num_key_value_heads": 6,
|
| 15 |
+
"pad_token_id": 0,
|
| 16 |
+
"rms_norm_eps": 1e-05,
|
| 17 |
+
"rope_theta": 10000.0,
|
| 18 |
+
"tie_word_embeddings": false,
|
| 19 |
+
"transformers_version": "5.2.0",
|
| 20 |
+
"use_cache": false,
|
| 21 |
+
"vocab_size": 32000
|
| 22 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "5.2.0"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c2fceaf00e1a8b8c97487cd874fe0c19c10d4f39b2efe40b4998106e228d042
|
| 3 |
+
size 932882120
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"cls_token": "<cls>",
|
| 5 |
+
"eos_token": "<eos>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"sep_token": "<sep>",
|
| 11 |
+
"tokenizer_class": "TokenizersBackend",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b787d1986e2fba02a7cc1ace6c39ec7c8d5b5c70b35f2af69cc93e42bc42f30a
|
| 3 |
+
size 5201
|