failspy commited on
Commit
dddab25
1 Parent(s): 2b1dff5

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -6,7 +6,7 @@
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "eos_token_id": 128009,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
@@ -22,7 +22,7 @@
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.40.2",
26
  "use_cache": true,
27
  "vocab_size": 128256
28
  }
 
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
 
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.1",
26
  "use_cache": true,
27
  "vocab_size": 128256
28
  }
generation_config.json CHANGED
@@ -1,12 +1,9 @@
1
  {
2
  "bos_token_id": 128000,
 
3
  "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128009
7
- ],
8
- "max_length": 4096,
9
  "temperature": 0.6,
 
10
  "top_p": 0.9,
11
- "transformers_version": "4.40.2"
12
  }
 
1
  {
2
  "bos_token_id": 128000,
3
+ "eos_token_id": [128001, 128009],
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
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b68af1913b8b787ec3d9bd52c3d91c2012a1f1ff1f04bfd16430025af633d105
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceed35eb31dfe11af54f56118d71d24848c296d1edaac03716a14c1f8251d5df
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f568931d63509847053f06e1f4b5c500eb942c3bc8fff36445f5c98f30383f
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e9ad31c8c32abf3a55ee7fc7217b3ecb35fd3c74d98a5bd233e0e4d6964f46
3
+ size 1168138808
special_tokens_map.json CHANGED
@@ -1,23 +1,4 @@
1
  {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|eot_id|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|end_of_text|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<|begin_of_text|>",
3
+ "eos_token": "<|end_of_text|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  }
tokenizer.json CHANGED
@@ -2329,10 +2329,69 @@
2329
  ]
2330
  },
2331
  "post_processor": {
2332
- "type": "ByteLevel",
2333
- "add_prefix_space": true,
2334
- "trim_offsets": false,
2335
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2336
  },
2337
  "decoder": {
2338
  "type": "ByteLevel",
@@ -2348,7 +2407,7 @@
2348
  "end_of_word_suffix": null,
2349
  "fuse_unk": false,
2350
  "byte_fallback": false,
2351
- "ignore_merges": false,
2352
  "vocab": {
2353
  "!": 0,
2354
  "\"": 1,
 
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",
 
2407
  "end_of_word_suffix": null,
2408
  "fuse_unk": false,
2409
  "byte_fallback": false,
2410
+ "ignore_merges": true,
2411
  "vocab": {
2412
  "!": 0,
2413
  "\"": 1,
tokenizer_config.json CHANGED
@@ -2059,4 +2059,4 @@
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
- }
 
2059
  ],
2060
  "model_max_length": 1000000000000000019884624838656,
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }