Chess Challenge submission by stephecw

README.md

@@ -14,7 +14,7 @@ Chess model submitted to the LLM Course Chess Challenge.
 ## Submission Info
 
 - **Submitted by**: [stephecw](https://huggingface.co/stephecw)
-- **Parameters**: 997,488
+- **Parameters**: 1,000,572
 - **Organization**: LLM-course
 
 ## Model Details
@@ -23,4 +23,4 @@ Chess model submitted to the LLM Course Chess Challenge.
 - **Vocab size**: 72
 - **Embedding dim**: 128
 - **Layers**: 6
-- **Heads**: 8
+- **Heads**: 4

config.json

@@ -10,8 +10,8 @@
   "model_type": "chess_transformer",
   "n_ctx": 256,
   "n_embd": 128,
-  "n_head": 8,
-  "n_inner": 360,
+  "n_head": 4,
+  "n_inner": 362,
   "n_layer": 6,
   "pad_token_id": 0,
   "tie_weights": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed6b993610a9a92698eade027262770e82fc310fa749d5cc66d4fe7172ed00b
-size 3996400
+oid sha256:251d42045988ec1c3601575b78e0a512e9e5c299f8e309e8ef8d5471160dada5
+size 4008736