Training in progress, step 1000
Browse files- config.json +30 -0
- model.safetensors +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +10 -0
- training_args.bin +3 -0
- vocab.json +1 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "chess-llama/config.json",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"eos_token_id": 1,
|
| 10 |
+
"head_dim": 32,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 20,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.47.0",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 80
|
| 30 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dca4c6540efd919b115082c88f1b8782d662b0cb3fe4af8b0150f11d4255fd91
|
| 3 |
+
size 608606432
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"clean_up_tokenization_spaces": false,
|
| 4 |
+
"extra_special_tokens": {},
|
| 5 |
+
"model_max_length": 2048,
|
| 6 |
+
"pad_token": "<|pad|>",
|
| 7 |
+
"padding_side": "right",
|
| 8 |
+
"tokenizer_class": "ChessTokenizer",
|
| 9 |
+
"unk_token": "<|unk|>"
|
| 10 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cac72eded41e9d4d87e3f89acba8d13767aa3b69f04527ff8b9cc8ffbe4bfc3a
|
| 3 |
+
size 5432
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<|start|>": 0, "<|turn|>": 1, "<|end|>": 2, "<|pad|>": 3, "<|unk|>": 4, "h1": 5, "h2": 6, "h3": 7, "h4": 8, "h5": 9, "h6": 10, "h7": 11, "h8": 12, "g1": 13, "g2": 14, "g3": 15, "g4": 16, "g5": 17, "g6": 18, "g7": 19, "g8": 20, "f1": 21, "f2": 22, "f3": 23, "f4": 24, "f5": 25, "f6": 26, "f7": 27, "f8": 28, "e1": 29, "e2": 30, "e3": 31, "e4": 32, "e5": 33, "e6": 34, "e7": 35, "e8": 36, "d1": 37, "d2": 38, "d3": 39, "d4": 40, "d5": 41, "d6": 42, "d7": 43, "d8": 44, "c1": 45, "c2": 46, "c3": 47, "c4": 48, "c5": 49, "c6": 50, "c7": 51, "c8": 52, "b1": 53, "b2": 54, "b3": 55, "b4": 56, "b5": 57, "b6": 58, "b7": 59, "b8": 60, "a1": 61, "a2": 62, "a3": 63, "a4": 64, "a5": 65, "a6": 66, "a7": 67, "a8": 68, "q": 69, "r": 70, "b": 71, "n": 72}
|