Upload folder using huggingface_hub
Browse files- README.md +1 -0
- config.json +0 -62
README.md
CHANGED
|
@@ -93,6 +93,7 @@ config.num_attention_heads = 8
|
|
| 93 |
config.num_hidden_layers = 2
|
| 94 |
config.max_window_layers = 1
|
| 95 |
config.tie_word_embeddings = False
|
|
|
|
| 96 |
model = AutoModelForCausalLM.from_config(
|
| 97 |
config,
|
| 98 |
torch_dtype=torch.bfloat16,
|
|
|
|
| 93 |
config.num_hidden_layers = 2
|
| 94 |
config.max_window_layers = 1
|
| 95 |
config.tie_word_embeddings = False
|
| 96 |
+
config.layer_types = ['full_attention'] * 2
|
| 97 |
model = AutoModelForCausalLM.from_config(
|
| 98 |
config,
|
| 99 |
torch_dtype=torch.bfloat16,
|
config.json
CHANGED
|
@@ -12,68 +12,6 @@
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 32,
|
| 14 |
"layer_types": [
|
| 15 |
-
"full_attention",
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention",
|
| 52 |
-
"full_attention",
|
| 53 |
-
"full_attention",
|
| 54 |
-
"full_attention",
|
| 55 |
-
"full_attention",
|
| 56 |
-
"full_attention",
|
| 57 |
-
"full_attention",
|
| 58 |
-
"full_attention",
|
| 59 |
-
"full_attention",
|
| 60 |
-
"full_attention",
|
| 61 |
-
"full_attention",
|
| 62 |
-
"full_attention",
|
| 63 |
-
"full_attention",
|
| 64 |
-
"full_attention",
|
| 65 |
-
"full_attention",
|
| 66 |
-
"full_attention",
|
| 67 |
-
"full_attention",
|
| 68 |
-
"full_attention",
|
| 69 |
-
"full_attention",
|
| 70 |
-
"full_attention",
|
| 71 |
-
"full_attention",
|
| 72 |
-
"full_attention",
|
| 73 |
-
"full_attention",
|
| 74 |
-
"full_attention",
|
| 75 |
-
"full_attention",
|
| 76 |
-
"full_attention",
|
| 77 |
"full_attention",
|
| 78 |
"full_attention"
|
| 79 |
],
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 32,
|
| 14 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"full_attention",
|
| 16 |
"full_attention"
|
| 17 |
],
|