Add trained cross-attention chess explainer weights
Browse files- .gitattributes +1 -0
- chat_template.jinja +4 -0
- tokenizer.json +3 -0
- tokenizer_config.json +17 -0
- trainable_params.pt +3 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -43,3 +43,4 @@ checkpoint-14539/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 43 |
checkpoint-16616/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
checkpoint-18693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
checkpoint-20770/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 43 |
checkpoint-16616/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
checkpoint-18693/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
checkpoint-20770/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '
|
| 2 |
+
' + message['content'] | trim + '<end_of_turn>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model
|
| 4 |
+
'}}{% endif %}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdc0fd8410449f9ab91a0bc149a04e4f2565ef5d608b588c971e500863286adf
|
| 3 |
+
size 34362526
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<bos>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<eos>",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"spaces_between_special_tokens": false,
|
| 14 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 15 |
+
"unk_token": "<unk>",
|
| 16 |
+
"use_default_system_prompt": false
|
| 17 |
+
}
|
trainable_params.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:820ef35e4e6a3f25de44f7048c514c225ca5725d908b80b15de0d4d34f85735d
|
| 3 |
+
size 18815091
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bb2c1c94aa0fdd3230268e016f0540025019dc2d2135c0ef925a101aa0459fa
|
| 3 |
+
size 5265
|