Hazzzardous SmerkyG commited on
Commit
d48d1c5
0 Parent(s):

Duplicate from SmerkyG/rwkv-5-world-all-pth

Browse files

Co-authored-by: Dan Goldstein <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ - zh
5
+ - fr
6
+ - es
7
+ - de
8
+ - pt
9
+ - ru
10
+ - it
11
+ - ja
12
+ - ko
13
+ - vi
14
+ - ar
15
+ tags:
16
+ - pytorch
17
+ - text-generation
18
+ - causal-lm
19
+ - rwkv
20
+ license: apache-2.0
21
+ datasets:
22
+ - cerebras/SlimPajama-627B
23
+ - EleutherAI/pile
24
+ - bigcode/starcoderdata
25
+ - oscar-corpus/OSCAR-2301
26
+ ---
27
+
28
+ # RWKV-5 World
29
+
30
+ Use rwkv pip package 0.8.22+ for RWKV-5 inference: https://pypi.org/project/rwkv/ (pipeline = PIPELINE(model, "rwkv_vocab_v20230424") for rwkv-world models)
31
+
32
+ Online 7B Demo: https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-2
33
+
34
+ Online 1.5B Demo: https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-1
35
+
36
+ GUI: https://github.com/josStorer/RWKV-Runner (see Releases)
37
+
38
+ Convert to HF formet: https://github.com/BBuf/RWKV-World-HF-Tokenizer
39
+
40
+ For developer: https://github.com/BlinkDL/ChatRWKV/blob/main/API_DEMO_CHAT.py
41
+
42
+ https://github.com/BlinkDL/ChatRWKV/blob/main/RWKV_v5_demo.py
43
+
44
+ How it works: https://twitter.com/BlinkDL_AI/status/1685230712247795713
45
+
46
+ https://www.rwkv.com/
47
+
48
+ ## Model Description
49
+
50
+ RWKV-5 trained on 100+ world languages (70% English, 15% multilang, 15% code).
51
+
52
+ World = Some_Pile + Some_SlimPajama + Some_StarCoder + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find
53
+
54
+ RWKV-5 training: set --my_testing "r2r4" in latest RWKV-LM v4neo: https://github.com/BlinkDL/RWKV-LM
55
+
56
+ World v1 = 0.59T tokens
57
+
58
+ World v2 = 1.12T tokens
59
+
60
+ Imagine what happens when we use more data :)
61
+
62
+ Recommended fine-tuning format (use \n for newlines):
63
+ ```
64
+ User: xxxxxxxxxxxxxxx
65
+
66
+ Assistant: xxxxxxxxxxxxxxx
67
+ xxxxxxxxxxxxxxx
68
+ xxxxxxxxxxxxxxx
69
+
70
+ User: xxxxxxxxxxxxxxx
71
+ xxxxxxxxxxxxxxx
72
+
73
+ Assistant: xxxxxxxxxxxxxxx
74
+ xxxxxxxxxxxxxxx
75
+ xxxxxxxxxxxxxxx
76
+ xxxxxxxxxxxxxxx
77
+ ```
78
+
79
+ A good chat prompt (better replace \n\n in xxx to \n, such that there will be no newlines in xxx):
80
+ ```
81
+ User: hi
82
+
83
+ Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
84
+
85
+ User: xxx
86
+
87
+ Assistant:
88
+ ```
89
+ QA prompt (better replace \n\n in xxx to \n, such that there will be no newlines in xxx):
90
+ ```
91
+ Question: xxx
92
+
93
+ Answer:
94
+ ```
95
+ and
96
+ ```
97
+ Instruction: xxx
98
+
99
+ Input: xxx
100
+
101
+ Response:
102
+ ```
103
+
104
+ !!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!
105
+
106
+ !!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!
107
+
108
+ !!! There should not be any space after your final ":" or you will upset the tokenizer and see non-English reponse !!!
RWKV-5-World-0.4B-v2-20231113-ctx4096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a288c54c7f30b0e2d4af23991133fad2af2d5e59ec7ad850ffe78054a5e4f92
3
+ size 923523954
RWKV-5-World-1B5-v2-20231025-ctx4096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a89f56be7f82ab9dd0835af9a6838f788477471616c02f7b041e3aea0c57435
3
+ size 3155590194
RWKV-5-World-3B-v2-20231113-ctx4096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bd430343c6fd138b85bbc68bb20262d3a2f053ea57dc4b41078269af68ff9c
3
+ size 6126106674
RWKV-5-World-3B-v2-20231118-ctx16k.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa5178d1c824b94ef17c6c9a456674e5581a8be832becbda9aba4dc533f88c2
3
+ size 6126106467
RWKV-5-World-7B-v2-20240128-ctx4096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88c7274184b211e5545c8f992f0b80d03c40a447980bbfcd0f6d5858982615a
3
+ size 15036197526