Transformers
GGUF
English
Inference Endpoints
maddes8cht commited on
Commit
5c75e6f
1 Parent(s): 5926e8a

"Update README.md"

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - totally-not-an-llm/EverythingLM-data-V2-sharegpt
5
+ language:
6
+ - en
7
+ library_name: transformers
8
+ ---
9
+ [![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]()
10
+
11
+ I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
12
+
13
+ # open-llama-3b-everything-v2 - GGUF
14
+ - Model creator: [harborwater](https://huggingface.co/harborwater)
15
+ - Original model: [open-llama-3b-everything-v2](https://huggingface.co/harborwater/open-llama-3b-everything-v2)
16
+
17
+ OpenLlama is a free reimplementation of the original Llama Model which is licensed under Apache 2 license.
18
+
19
+
20
+
21
+ # About GGUF format
22
+
23
+ `gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.
24
+ A growing list of Software is using it and can therefore use this model.
25
+ The core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov
26
+
27
+ # Quantization variants
28
+
29
+ There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:
30
+
31
+ # Legacy quants
32
+
33
+ Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
34
+ Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
35
+ ## Note:
36
+ Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.
37
+ (This mainly refers to Falcon 7b and Starcoder models)
38
+
39
+ # K-quants
40
+
41
+ K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.
42
+ So, if possible, use K-quants.
43
+ With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
44
+
45
+
46
+
47
+
48
+ ---
49
+
50
+ # Original Model Card:
51
+ Trained on 3 epochs of the `totally-not-an-llm/EverythingLM-data-V2-sharegpt` dataset.
52
+ ```
53
+ ### HUMAN:
54
+ {prompt}
55
+
56
+ ### RESPONSE:
57
+ <leave a newline for the model to answer>
58
+ ```
59
+
60
+
61
+ note: Changed a few of the finetuning parameters this time around. I have no idea if its any good but Feel free to give it a try!
62
+
63
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
64
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
65
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_harborwater__open-llama-3b-everything-v2)
66
+
67
+ | Metric | Value |
68
+ |-----------------------|---------------------------|
69
+ | Avg. | 36.29 |
70
+ | ARC (25-shot) | 42.83 |
71
+ | HellaSwag (10-shot) | 73.28 |
72
+ | MMLU (5-shot) | 26.87 |
73
+ | TruthfulQA (0-shot) | 37.26 |
74
+ | Winogrande (5-shot) | 66.61 |
75
+ | GSM8K (5-shot) | 1.59 |
76
+ | DROP (3-shot) | 5.61 |
77
+
78
+ ***End of original Model File***
79
+ ---
80
+
81
+
82
+ ## Please consider to support my work
83
+ **Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
84
+
85
+ <center>
86
+
87
+ [![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io)
88
+ [![Stack Exchange](https://stackexchange.com/users/flair/26485911.png)](https://stackexchange.com/users/26485911)
89
+ [![GitHub](https://maddes8cht.github.io/assets/buttons/github-button.png)](https://github.com/maddes8cht)
90
+ [![HuggingFace](https://maddes8cht.github.io/assets/buttons/huggingface-button.png)](https://huggingface.co/maddes8cht)
91
+ [![Twitter](https://maddes8cht.github.io/assets/buttons/twitter-button.png)](https://twitter.com/maddes1966)
92
+
93
+ </center>