Update checkpoint from thanhdath/FINER-SQL-3B-BIRD + add GitHub link
Browse filesMirrors the latest FINER-SQL-3B-BIRD weights from thanhdath/. README adds the GitHub repo link.
- config.json +1 -1
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- tokenizer_config.json +3 -1
config.json
CHANGED
|
@@ -59,7 +59,7 @@
|
|
| 59 |
"rope_theta": 1000000.0,
|
| 60 |
"sliding_window": null,
|
| 61 |
"tie_word_embeddings": true,
|
| 62 |
-
"transformers_version": "4.57.
|
| 63 |
"use_cache": false,
|
| 64 |
"use_sliding_window": false,
|
| 65 |
"vocab_size": 151936
|
|
|
|
| 59 |
"rope_theta": 1000000.0,
|
| 60 |
"sliding_window": null,
|
| 61 |
"tie_word_embeddings": true,
|
| 62 |
+
"transformers_version": "4.57.3",
|
| 63 |
"use_cache": false,
|
| 64 |
"use_sliding_window": false,
|
| 65 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "4.57.
|
| 13 |
}
|
|
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4957560304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee02a3811c46f66e0b9fb703a474b9996ea71d30b822aa900ea3b46c0e609cf1
|
| 3 |
size 4957560304
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1214366696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb660d6e329abcb9105a8183eb58798c4937d2a33e2e1e2c8ee43fa622fe888e
|
| 3 |
size 1214366696
|
tokenizer_config.json
CHANGED
|
@@ -201,12 +201,14 @@
|
|
| 201 |
"extra_special_tokens": {},
|
| 202 |
"max_length": 6192,
|
| 203 |
"model_max_length": 32768,
|
|
|
|
| 204 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 205 |
"padding_side": "left",
|
| 206 |
"split_special_tokens": false,
|
| 207 |
"stride": 0,
|
| 208 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 209 |
-
"truncation_side": "
|
| 210 |
"truncation_strategy": "longest_first",
|
| 211 |
"unk_token": null
|
| 212 |
}
|
|
|
|
| 201 |
"extra_special_tokens": {},
|
| 202 |
"max_length": 6192,
|
| 203 |
"model_max_length": 32768,
|
| 204 |
+
"pad_to_multiple_of": null,
|
| 205 |
"pad_token": "<|endoftext|>",
|
| 206 |
+
"pad_token_type_id": 0,
|
| 207 |
"padding_side": "left",
|
| 208 |
"split_special_tokens": false,
|
| 209 |
"stride": 0,
|
| 210 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 211 |
+
"truncation_side": "left",
|
| 212 |
"truncation_strategy": "longest_first",
|
| 213 |
"unk_token": null
|
| 214 |
}
|