Upload folder using huggingface_hub
Browse files- generation_config.json +5 -2
- tokenizer.json +63 -4
- tokenizer_config.json +0 -1
generation_config.json
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
5 |
"transformers_version": "4.40.0.dev0"
|
6 |
}
|
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 128000,
|
3 |
+
"eos_token_id": 128001,
|
4 |
+
"do_sample": true,
|
5 |
+
"temperature": 0.6,
|
6 |
+
"max_length": 4096,
|
7 |
+
"top_p": 0.9,
|
8 |
"transformers_version": "4.40.0.dev0"
|
9 |
}
|
tokenizer.json
CHANGED
@@ -2329,10 +2329,69 @@
|
|
2329 |
]
|
2330 |
},
|
2331 |
"post_processor": {
|
2332 |
-
"type": "
|
2333 |
-
"
|
2334 |
-
|
2335 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2336 |
},
|
2337 |
"decoder": {
|
2338 |
"type": "ByteLevel",
|
|
|
2329 |
]
|
2330 |
},
|
2331 |
"post_processor": {
|
2332 |
+
"type": "Sequence",
|
2333 |
+
"processors": [
|
2334 |
+
{
|
2335 |
+
"type": "ByteLevel",
|
2336 |
+
"add_prefix_space": true,
|
2337 |
+
"trim_offsets": false,
|
2338 |
+
"use_regex": true
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"type": "TemplateProcessing",
|
2342 |
+
"single": [
|
2343 |
+
{
|
2344 |
+
"SpecialToken": {
|
2345 |
+
"id": "<|begin_of_text|>",
|
2346 |
+
"type_id": 0
|
2347 |
+
}
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"Sequence": {
|
2351 |
+
"id": "A",
|
2352 |
+
"type_id": 0
|
2353 |
+
}
|
2354 |
+
}
|
2355 |
+
],
|
2356 |
+
"pair": [
|
2357 |
+
{
|
2358 |
+
"SpecialToken": {
|
2359 |
+
"id": "<|begin_of_text|>",
|
2360 |
+
"type_id": 0
|
2361 |
+
}
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"Sequence": {
|
2365 |
+
"id": "A",
|
2366 |
+
"type_id": 0
|
2367 |
+
}
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"SpecialToken": {
|
2371 |
+
"id": "<|begin_of_text|>",
|
2372 |
+
"type_id": 1
|
2373 |
+
}
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"Sequence": {
|
2377 |
+
"id": "B",
|
2378 |
+
"type_id": 1
|
2379 |
+
}
|
2380 |
+
}
|
2381 |
+
],
|
2382 |
+
"special_tokens": {
|
2383 |
+
"<|begin_of_text|>": {
|
2384 |
+
"id": "<|begin_of_text|>",
|
2385 |
+
"ids": [
|
2386 |
+
128000
|
2387 |
+
],
|
2388 |
+
"tokens": [
|
2389 |
+
"<|begin_of_text|>"
|
2390 |
+
]
|
2391 |
+
}
|
2392 |
+
}
|
2393 |
+
}
|
2394 |
+
]
|
2395 |
},
|
2396 |
"decoder": {
|
2397 |
"type": "ByteLevel",
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,6 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|end_of_text|>",
|
2056 |
"model_input_names": [
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|