jbgjbg commited on
Commit
b060f97
·
verified ·
1 Parent(s): 7d93b79

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_remove_final_layer_norm": false,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "OPTForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 2,
10
+ "do_layer_norm_before": true,
11
+ "dropout": 0.1,
12
+ "enable_bias": true,
13
+ "eos_token_id": 2,
14
+ "ffn_dim": 36864,
15
+ "hidden_size": 9216,
16
+ "init_std": 0.02,
17
+ "layer_norm_elementwise_affine": true,
18
+ "layerdrop": 0.0,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "opt",
21
+ "num_attention_heads": 72,
22
+ "num_hidden_layers": 64,
23
+ "pad_token_id": 1,
24
+ "prefix": "</s>",
25
+ "quantization_config": {
26
+ "config_groups": {
27
+ "group_0": {
28
+ "format": "float-quantized",
29
+ "input_activations": {
30
+ "actorder": null,
31
+ "block_structure": null,
32
+ "dynamic": true,
33
+ "group_size": 128,
34
+ "num_bits": 8,
35
+ "observer": null,
36
+ "observer_kwargs": {},
37
+ "strategy": "group",
38
+ "symmetric": true,
39
+ "type": "float"
40
+ },
41
+ "output_activations": null,
42
+ "targets": [
43
+ "Linear"
44
+ ],
45
+ "weights": {
46
+ "actorder": null,
47
+ "block_structure": [
48
+ 128,
49
+ 128
50
+ ],
51
+ "dynamic": false,
52
+ "group_size": null,
53
+ "num_bits": 8,
54
+ "observer": "minmax",
55
+ "observer_kwargs": {},
56
+ "strategy": "block",
57
+ "symmetric": true,
58
+ "type": "float"
59
+ }
60
+ }
61
+ },
62
+ "format": "float-quantized",
63
+ "global_compression_ratio": null,
64
+ "ignore": [
65
+ "lm_head"
66
+ ],
67
+ "kv_cache_scheme": null,
68
+ "quant_method": "compressed-tensors",
69
+ "quantization_status": "compressed",
70
+ "sparsity_config": {},
71
+ "transform_config": {},
72
+ "version": "0.11.1.dev0"
73
+ },
74
+ "tie_word_embeddings": false,
75
+ "torch_dtype": "float16",
76
+ "transformers_version": "4.55.2",
77
+ "use_cache": true,
78
+ "vocab_size": 50272,
79
+ "word_embed_proj_dim": 9216
80
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.55.2"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af4ee1c031b07b4973c895c0f91ca87a588f869182454d6a335cf37b6d242d10
3
+ size 4702930528
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c76cfc98106cbd038bdf9c8efbe9200202f73a9eff166b5d7cdbc494875c7c
3
+ size 4758058032
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd14faf81b478daeece1991ad4e913e26d62fb26455f03702856d578e3d9f513
3
+ size 4927947512
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0b857c09139fec87df1567bfd86cf220b73792730080cb6c75decff6ca2c3d
3
+ size 4927984648
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ab3b7815dadd5b149da5970a19156fd935fbb80a169d531a3b63a29f2a8e78
3
+ size 4758076344
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255dd12633d4d0a998bff2c540e42458ecf4b29656eed73b38e3fde4a37e9fb3
3
+ size 4758058136
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461fdec0aab6e1e91bdf6f019a4688981504d77a67e48d1c7b97862f7ef190ea
3
+ size 4927947560
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31323d361fbf6847ca2165116a0034b235c92d1c96d0ab44fccc60dac140aed1
3
+ size 4927984648
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd0477a0f86f1217b5d7260bd0be5975be8cba9ffef1fbc3bb99cbf44641607
3
+ size 4758076344
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca9e6587cc063e90609e1aa0d35da1327de5bff6758f9b3d943cb9c5670439
3
+ size 4758058136
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c08205ce8b73a9072be3736fcf6032fe866c894e54194bf365a7000367fac34
3
+ size 4927947560
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17ecd05602b7db21dfd0bdde6dc5233ae0627d77fd53a17b7d1bba7f8ab94a1
3
+ size 4927984648
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d575261d4bfb86da6954f4339b91ae1eafe7566fd2a3f76d39439a03ac8e65dc
3
+ size 4758076344
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a5794e3d416ba32effccd8068bfe2ff218c47bfe2b9233c11cdca039f076b7
3
+ size 4325197184
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: FP8_BLOCK
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "extra_special_tokens": {},
27
+ "model_max_length": 1000000000000000019884624838656,
28
+ "pad_token": "<pad>",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "</s>"
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff