smsk-01 commited on
Commit
231122e
·
verified ·
1 Parent(s): 1222afa

Chess Challenge submission by smsk-01

Browse files
Files changed (3) hide show
  1. README.md +3 -3
  2. config.json +3 -2
  3. model.safetensors +2 -2
README.md CHANGED
@@ -14,7 +14,7 @@ Chess model submitted to the LLM Course Chess Challenge.
14
  ## Submission Info
15
 
16
  - **Submitted by**: [smsk-01](https://huggingface.co/smsk-01)
17
- - **Parameters**: 909,824
18
  - **Organization**: LLM-course
19
 
20
  ## Model Details
@@ -22,5 +22,5 @@ Chess model submitted to the LLM Course Chess Challenge.
22
  - **Architecture**: Chess Transformer (GPT-style)
23
  - **Vocab size**: 1682
24
  - **Embedding dim**: 128
25
- - **Layers**: 4
26
- - **Heads**: 4
 
14
  ## Submission Info
15
 
16
  - **Submitted by**: [smsk-01](https://huggingface.co/smsk-01)
17
+ - **Parameters**: 579,072
18
  - **Organization**: LLM-course
19
 
20
  ## Model Details
 
22
  - **Architecture**: Chess Transformer (GPT-style)
23
  - **Vocab size**: 1682
24
  - **Embedding dim**: 128
25
+ - **Layers**: 2
26
+ - **Heads**: 8
config.json CHANGED
@@ -10,9 +10,10 @@
10
  "model_type": "chess_transformer",
11
  "n_ctx": 256,
12
  "n_embd": 128,
13
- "n_head": 4,
14
  "n_inner": 384,
15
- "n_layer": 4,
 
16
  "pad_token_id": 0,
17
  "tie_weights": true,
18
  "transformers_version": "4.57.3",
 
10
  "model_type": "chess_transformer",
11
  "n_ctx": 256,
12
  "n_embd": 128,
13
+ "n_head": 8,
14
  "n_inner": 384,
15
+ "n_layer": 2,
16
+ "n_recur": 3,
17
  "pad_token_id": 0,
18
  "tie_weights": true,
19
  "transformers_version": "4.57.3",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3226e768d2ba7e49c1f80f65c6485a67baae480b3b8ecb0bee2e2016c016eaf8
3
- size 3643696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19844313ae41722dfdd0648e4645491d682f45b4c9350b17defb5305c7336a98
3
+ size 2318640