Lin-K76 commited on
Commit
330f3af
·
verified ·
1 Parent(s): d61f2de

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,51 +1,10 @@
1
  {
2
- "_name_or_path": "/home/meta-llama/Meta-Llama-3.1-405B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "compression_config": {
10
- "config_groups": {
11
- "group_0": {
12
- "input_activations": {
13
- "block_structure": null,
14
- "dynamic": false,
15
- "group_size": null,
16
- "num_bits": 8,
17
- "observer": "minmax",
18
- "observer_kwargs": {},
19
- "strategy": "tensor",
20
- "symmetric": true,
21
- "type": "float"
22
- },
23
- "output_activations": null,
24
- "targets": [
25
- "Linear"
26
- ],
27
- "weights": {
28
- "block_structure": null,
29
- "dynamic": false,
30
- "group_size": null,
31
- "num_bits": 8,
32
- "observer": "minmax",
33
- "observer_kwargs": {},
34
- "strategy": "tensor",
35
- "symmetric": true,
36
- "type": "float"
37
- }
38
- }
39
- },
40
- "format": "naive-quantized",
41
- "global_compression_ratio": 1.4646996824138383,
42
- "ignore": [
43
- "lm_head"
44
- ],
45
- "kv_cache_scheme": null,
46
- "quant_method": "compressed-tensors",
47
- "quantization_status": "frozen"
48
- },
49
  "eos_token_id": [
50
  128001,
51
  128008,
@@ -63,11 +22,17 @@
63
  "num_key_value_heads": 16,
64
  "pretraining_tp": 1,
65
  "rms_norm_eps": 1e-05,
66
- "rope_scaling": null,
 
 
 
 
 
 
67
  "rope_theta": 500000.0,
68
  "tie_word_embeddings": false,
69
- "torch_dtype": "float16",
70
- "transformers_version": "4.43.1",
71
  "use_cache": true,
72
  "vocab_size": 128256
73
- }
 
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 128000,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "eos_token_id": [
9
  128001,
10
  128008,
 
22
  "num_key_value_heads": 16,
23
  "pretraining_tp": 1,
24
  "rms_norm_eps": 1e-05,
25
+ "rope_scaling": {
26
+ "factor": 8.0,
27
+ "low_freq_factor": 1.0,
28
+ "high_freq_factor": 4.0,
29
+ "original_max_position_embeddings": 8192,
30
+ "rope_type": "llama3"
31
+ },
32
  "rope_theta": 500000.0,
33
  "tie_word_embeddings": false,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.42.3",
36
  "use_cache": true,
37
  "vocab_size": 128256
38
+ }
generation_config.json CHANGED
@@ -1,10 +1,12 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 128000,
 
4
  "eos_token_id": [
5
  128001,
6
  128008,
7
  128009
8
  ],
9
- "transformers_version": "4.43.1"
10
- }
 
 
 
1
  {
 
2
  "bos_token_id": 128000,
3
+ "do_sample": true,
4
  "eos_token_id": [
5
  128001,
6
  128008,
7
  128009
8
  ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.42.3"
12
+ }
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -12,6 +12,5 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
- },
16
- "pad_token": "<|eot_id|>"
17
  }
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
+ }
 
16
  }
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",
 
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
@@ -2058,6 +2058,5 @@
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }