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**: 960,480
+- **Parameters**: 1,003,656
 - **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**: 4
+- **Heads**: 8

config.json

@@ -10,8 +10,8 @@
   "model_type": "chess_transformer",
   "n_ctx": 256,
   "n_embd": 128,
-  "n_head": 4,
-  "n_inner": 336,
+  "n_head": 8,
+  "n_inner": 364,
   "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 sha256:9922467d048ed4a5bbff9895d35c1444d8c2ab0c0fdb2f4c843142613891e5db
-size 3848368
+oid sha256:24ba99e14c30c1834e13da087ee6ac20e8c8d4ae1d15cd2825f570b434becc84
+size 4021072