Training in progress, step 10000
Browse files- config.json +28 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GemmaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"eos_token_id": 1,
|
| 9 |
+
"head_dim": 256,
|
| 10 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 11 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 16384,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"model_type": "gemma",
|
| 17 |
+
"num_attention_heads": 8,
|
| 18 |
+
"num_hidden_layers": 18,
|
| 19 |
+
"num_image_tokens": 256,
|
| 20 |
+
"num_key_value_heads": 1,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.42.4",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 257216
|
| 28 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a1fd68415535884cc11060d5583cec7ef6cfd1bd6307efd7fb9f4cab015da30
|
| 3 |
+
size 5176
|