Felladrin commited on
Commit
c360bdf
·
1 Parent(s): 58eb09d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md CHANGED
@@ -1,3 +1,99 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - text-generation
7
+ base_model: BEE-spoke-data/smol_llama-101M-GQA
8
+ datasets:
9
+ - Open-Orca/SlimOrca-Dedup
10
+ - VMware/open-instruct
11
+ - LDJnr/Capybara
12
+ - cognitivecomputations/ultrachat-uncensored
13
+ - starfishmedical/webGPT_x_dolly
14
+ - THUDM/webglm-qa
15
+ widget:
16
+ - text: |-
17
+ <|im_start|>system
18
+ You are a helpful assistant who gives creative responses.<|im_end|>
19
+ <|im_start|>user
20
+ Write the background story of a game about wizards and llamas in a sci-fi world.<|im_end|>
21
+ <|im_start|>assistant
22
+ - text: |-
23
+ <|im_start|>system
24
+ A friendly chat between a user and an assistant.<|im_end|>
25
+ <|im_start|>user
26
+ Got a question for you!<|im_end|>
27
+ <|im_start|>assistant
28
+ Sure! What's it?<|im_end|>
29
+ <|im_start|>user
30
+ I need to build a simple website. Where should I start learning about web development?<|im_end|>
31
+ <|im_start|>assistant
32
+ - text: |-
33
+ <|im_start|>system
34
+ You are a helpful assistant, who always answers with empathy.<|im_end|>
35
+ <|im_start|>user
36
+ List the pros and cons of social media.<|im_end|>
37
+ <|im_start|>assistant
38
+ - text: |-
39
+ <|im_start|>system
40
+ You are a helpful assistant, who always answers with empathy.<|im_end|>
41
+ <|im_start|>user
42
+ Hello!<|im_end|>
43
+ <|im_start|>assistant
44
+ Hi! How can I help you today?<|im_end|>
45
+ <|im_start|>user
46
+ Take a look at the info below.
47
+
48
+ - The tape inside the VHS cassettes is very delicate and can be easily ruined, making them unplayable and unrepairable. The reason the tape deteriorates is that the magnetic charge needed for them to work is not permanent, and the magnetic particles end up losing their charge in a process known as remanence decay. These particles could also become demagnetised via being stored too close to a magnetic source.
49
+ - One of the most significant issues with VHS tapes is that they have moving parts, meaning that there are more occasions when something can go wrong, damaging your footage or preventing it from playing back. The tape itself is a prominent cause of this, and tape slippage can occur. Tapes slippage can be caused when the tape loses its tension, or it has become warped. These problems can occur in storage due to high temperatures or frequent changes in humidity.
50
+ - VHS tapes deteriorate over time from infrequent or overuse. Neglect means mold and dirt, while overuse can lead to scratches and technical difficulties. This is why old VHS tapes inevitably experience malfunctions after a long period of time. Usually anywhere between 10 to 25+ years.
51
+ - Some VHS tapes like newer mini DVs and Digital 8 tapes can suffer from digital corruption, meaning that the footage becomes lost and cannot be recovered. These tapes were the steppingstone from VHS to the digital age when capturing footage straight to digital became the norm. Unfortunately,they are susceptible to digital corruption, which causes video pixilation and/or loss of audio.<|im_end|>
52
+ <|im_start|>assistant
53
+ Alright!<|im_end|>
54
+ <|im_start|>user
55
+ Now I'm going to write my question, and if the info above is useful, you can use them in your response.
56
+ Ready?<|im_end|>
57
+ <|im_start|>assistant
58
+ Ready for your question!<|im_end|>
59
+ <|im_start|>user
60
+ Why do VHS tapes deteriorate over time?<|im_end|>
61
+ <|im_start|>assistant
62
+ inference:
63
+ parameters:
64
+ max_new_tokens: 250
65
+ penalty_alpha: 0.5
66
+ top_k: 5
67
  ---
68
+
69
+ # A Llama Chat Model of 101M Parameters
70
+
71
+ - Base model: [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA)
72
+ - Datasets:
73
+ - [Open-Orca/SlimOrca-Dedup](https://huggingface.co/datasets/Open-Orca/SlimOrca-Dedup)
74
+ - [VMware/open-instruct](https://huggingface.co/datasets/VMware/open-instruct)
75
+ - [LDJnr/Capybara](https://huggingface.co/datasets/LDJnr/Capybara)
76
+ - [cognitivecomputations/ultrachat-uncensored](https://huggingface.co/datasets/cognitivecomputations/ultrachat-uncensored)
77
+ - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly)
78
+ - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa)
79
+
80
+ ## Recommended Prompt Format
81
+
82
+ The recommended prompt format is as follows:
83
+
84
+ ```
85
+ <|im_start|>system
86
+ {system_message}<|im_end|>
87
+ <|im_start|>user
88
+ {user_message}<|im_end|>
89
+ <|im_start|>assistant
90
+ ```
91
+
92
+ ## Recommended Inference Parameters
93
+
94
+ To get the best results, prefer using [contrastive search](https://huggingface.co/docs/transformers/main/en/generation_strategies#contrastive-search) for inference:
95
+
96
+ ```yml
97
+ penalty_alpha: 0.5
98
+ top_k: 5
99
+ ```