Upload ZeroLayerTransformer

README.md

@@ -1,3 +1,6 @@
+---
+{}
+---
 0-layer transformer described in [A Mathematical Framework for Transformer Circuits](https://transformer-circuits.pub/2021/framework/index.html).Load with ```python
 class ZeroLayerTransformer(nn.Module, PyTorchModelHubMixin):
     def __init__(self, config):

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "ZeroLayerTransformer"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 0,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": false,
+  "vocab_size": 4096
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9be0e96ae59dcdece03c723514f25726d4ba7996327ac91b74e160cf2c7e91
-size 4194488
+oid sha256:9d5bc074b89fca80f75499f17ae2176e058625550802fe325fabf3bc2c7c2d24
+size 4194520