Chess Challenge submission by iliasslasri
Browse files- README.md +3 -3
- config.json +6 -6
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -14,13 +14,13 @@ Chess model submitted to the LLM Course Chess Challenge.
|
|
| 14 |
## Submission Info
|
| 15 |
|
| 16 |
- **Submitted by**: [iliasslasri](https://huggingface.co/iliasslasri)
|
| 17 |
-
- **Parameters**:
|
| 18 |
- **Organization**: LLM-course
|
| 19 |
|
| 20 |
## Model Details
|
| 21 |
|
| 22 |
- **Architecture**: Chess Transformer (GPT-style)
|
| 23 |
- **Vocab size**: 75
|
| 24 |
-
- **Embedding dim**:
|
| 25 |
- **Layers**: 11
|
| 26 |
-
- **Heads**:
|
|
|
|
| 14 |
## Submission Info
|
| 15 |
|
| 16 |
- **Submitted by**: [iliasslasri](https://huggingface.co/iliasslasri)
|
| 17 |
+
- **Parameters**: 980,720
|
| 18 |
- **Organization**: LLM-course
|
| 19 |
|
| 20 |
## Model Details
|
| 21 |
|
| 22 |
- **Architecture**: Chess Transformer (GPT-style)
|
| 23 |
- **Vocab size**: 75
|
| 24 |
+
- **Embedding dim**: 92
|
| 25 |
- **Layers**: 11
|
| 26 |
+
- **Heads**: 4
|
config.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "./
|
| 3 |
"architectures": [
|
| 4 |
"ChessForCausalLM"
|
| 5 |
],
|
| 6 |
-
"attn": "
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "model.ChessConfig",
|
| 9 |
"AutoModelForCausalLM": "model.ChessForCausalLM"
|
|
@@ -14,11 +14,11 @@
|
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
"model_type": "chess_transformer",
|
| 16 |
"n_ctx": 256,
|
| 17 |
-
"n_embd":
|
| 18 |
-
"n_head":
|
| 19 |
-
"n_inner":
|
| 20 |
"n_layer": 11,
|
| 21 |
-
"num_groups":
|
| 22 |
"pad_token_id": 0,
|
| 23 |
"tie_weights": false,
|
| 24 |
"tie_word_embeddings": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./11_4_92_ft_ft_ft/checkpoint-475008/",
|
| 3 |
"architectures": [
|
| 4 |
"ChessForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attn": "MHA",
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "model.ChessConfig",
|
| 9 |
"AutoModelForCausalLM": "model.ChessForCausalLM"
|
|
|
|
| 14 |
"layer_norm_epsilon": 1e-05,
|
| 15 |
"model_type": "chess_transformer",
|
| 16 |
"n_ctx": 256,
|
| 17 |
+
"n_embd": 92,
|
| 18 |
+
"n_head": 4,
|
| 19 |
+
"n_inner": 276,
|
| 20 |
"n_layer": 11,
|
| 21 |
+
"num_groups": 2,
|
| 22 |
"pad_token_id": 0,
|
| 23 |
"tie_weights": false,
|
| 24 |
"tie_word_embeddings": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f7244a5c854e9c9684f98b1b63970ad82899c0545f1fb1b105ce1ae2e8f76a8
|
| 3 |
+
size 3934384
|