coryg89 commited on
Commit
869a47a
1 Parent(s): d2149ea

First commit adding model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.model.bak filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+ - Yi
10
+ - exl2
11
+ - exllamav2
12
+ license_name: yi-license
13
+ license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
14
+ base_model: []
15
+ ---
16
+
17
+ # Yi-34B-200K-DARE-merge-v7-6bpw-exl2
18
+
19
+ Original model:
20
+ - [brucethemoose/Yi-34B-200K-DARE-megamerge-v7](https://huggingface.co/brucethemoose/Yi-34B-200K-DARE-megamerge-v7)
21
+
22
+ Available quants:
23
+
24
+ - [coryg89/Yi-34B-200K-DARE-merge-v7-3bpw-exl2](https://huggingface.co/coryg89/Yi-34B-200K-DARE-merge-v7-3bpw-exl2)
25
+ - [coryg89/Yi-34B-200K-DARE-merge-v7-4bpw-exl2](https://huggingface.co/coryg89/Yi-34B-200K-DARE-merge-v7-4bpw-exl2)
26
+ - [coryg89/Yi-34B-200K-DARE-merge-v7-5bpw-exl2](https://huggingface.co/coryg89/Yi-34B-200K-DARE-merge-v7-5bpw-exl2)
27
+ - [coryg89/Yi-34B-200K-DARE-merge-v7-6bpw-exl2](https://huggingface.co/coryg89/Yi-34B-200K-DARE-merge-v7-6bpw-exl2)
28
+ - [coryg89/Yi-34B-200K-DARE-merge-v7-8bpw-exl2](https://huggingface.co/coryg89/Yi-34B-200K-DARE-merge-v7-8bpw-exl2)
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 7168,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 20480,
14
+ "max_position_embeddings": 200000,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 56,
17
+ "num_hidden_layers": 60,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 5000000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": true,
28
+ "vocab_size": 64002,
29
+ "quantization_config": {
30
+ "quant_method": "exl2",
31
+ "version": "0.0.15",
32
+ "bits": 3.0,
33
+ "head_bits": 6,
34
+ "calibration": {
35
+ "rows": 100,
36
+ "length": 2048,
37
+ "dataset": "(default)"
38
+ }
39
+ }
40
+ }
output-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a32d651da12051e21d1598417f686424be3241d2d3dcbab13885a19a659929
3
+ size 4250531344
output-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5901758ad5ab095e55001367706463a32a1c4bacc9c513bfc09c62f46d999aa4
3
+ size 4294818936
output-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f422523b72b15eb7994443d1d7cc63719d210dace93abcc9a7b903078ef89e
3
+ size 4280450200
output-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae8bd68eef168849b6466cf61dc7f5b5a943f0a25b6358cf7acbd3b27ae058d7
3
+ size 1008039840
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "64000": {
30
+ "content": "<s>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "64001": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ }
45
+ },
46
+ "bos_token": "<|startoftext|>",
47
+ "clean_up_tokenization_spaces": false,
48
+ "eos_token": "<|endoftext|>",
49
+ "legacy": false,
50
+ "model_max_length": 200000,
51
+ "pad_token": "<unk>",
52
+ "padding_side": "right",
53
+ "sp_model_kwargs": {},
54
+ "spaces_between_special_tokens": false,
55
+ "tokenizer_class": "LlamaTokenizer",
56
+ "truncation_side": "right",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": false
59
+ }