Upload LLaMA model
Browse files- config.json +25 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LLaMAForHF"
|
| 4 |
+
],
|
| 5 |
+
"batch_size": 64,
|
| 6 |
+
"clip_grad_norm": 0.5,
|
| 7 |
+
"context_window": 64,
|
| 8 |
+
"dim": 192,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"epochs": 5,
|
| 11 |
+
"learning_rate": 0.0001,
|
| 12 |
+
"max_lr": 0.0003,
|
| 13 |
+
"max_seq_len": 128,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_heads": 8,
|
| 16 |
+
"num_layers": 4,
|
| 17 |
+
"test_split": 0.1,
|
| 18 |
+
"torch_dtype": "float32",
|
| 19 |
+
"train_split": 0.8,
|
| 20 |
+
"transformers_version": "4.41.2",
|
| 21 |
+
"val_split": 0.1,
|
| 22 |
+
"vocab_size": 2000,
|
| 23 |
+
"warmup_steps": 1000,
|
| 24 |
+
"weight_decay": 0.1
|
| 25 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:619773953f4da43e72f6f7859fc265a966ee58fcde2320de948b3e3721e72497
|
| 3 |
+
size 10181824
|