Triangle104 commited on
Commit
65cfe27
·
verified ·
1 Parent(s): d2ebe74

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +2 -49
README.md CHANGED
@@ -16,6 +16,8 @@ datasets:
16
  language:
17
  - en
18
  base_model: cognitivecomputations/Dolphin3.0-Mistral-24B
 
 
19
  tags:
20
  - llama-cpp
21
  - gguf-my-repo
@@ -25,55 +27,6 @@ tags:
25
  This model was converted to GGUF format from [`cognitivecomputations/Dolphin3.0-Mistral-24B`](https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
26
  Refer to the [original model card](https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B) for more details on the model.
27
 
28
- ---
29
- Sponsors
30
-
31
-
32
-
33
-
34
- Our appreciation for the generous sponsors of Dolphin 3.0:
35
-
36
-
37
- Dria https://x.com/driaforall - Inference Sponsor
38
- Chutes https://x.com/rayon_labs - Compute Sponsor
39
- Crusoe Cloud - Compute Sponsor
40
- Andreessen Horowitz - provided the grant that originally launched Dolphin
41
-
42
- What is Dolphin?
43
-
44
- Dolphin 3.0 is the next generation of the Dolphin series of
45
- instruct-tuned models. Designed to be the ultimate general purpose
46
- local model, enabling coding, math, agentic, function calling, and
47
- general use cases.
48
-
49
-
50
- Dolphin aims to be a general purpose instruct model, similar to the
51
- models behind ChatGPT, Claude, Gemini. But these models present
52
- problems for businesses seeking to include AI in their products.
53
-
54
-
55
- They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
56
- They maintain control of the model versions, sometimes changing
57
- things silently, or deprecating older models that your business relies
58
- on.
59
- They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
60
- They can see all your queries and they can potentially use that data
61
- in ways you wouldn't want.
62
- Dolphin, in contrast, is steerable and gives control to the system
63
- owner. You set the system prompt. You decide the alignment. You have
64
- control of your data. Dolphin does not impose its ethics or guidelines
65
- on you. You are the one who decides the guidelines.
66
-
67
-
68
- Dolphin belongs to YOU, it is your tool, an extension of your will.
69
- Just as you are personally responsible for what you do with a knife,
70
- gun, fire, car, or the internet, you are the creator and originator of
71
- any content you generate with Dolphin.
72
-
73
-
74
- https://erichartford.com/uncensored-models
75
-
76
- ---
77
  ## Use with llama.cpp
78
  Install llama.cpp through brew (works on Mac and Linux)
79
 
 
16
  language:
17
  - en
18
  base_model: cognitivecomputations/Dolphin3.0-Mistral-24B
19
+ pipeline_tag: text-generation
20
+ library_name: transformers
21
  tags:
22
  - llama-cpp
23
  - gguf-my-repo
 
27
  This model was converted to GGUF format from [`cognitivecomputations/Dolphin3.0-Mistral-24B`](https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
28
  Refer to the [original model card](https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B) for more details on the model.
29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  ## Use with llama.cpp
31
  Install llama.cpp through brew (works on Mac and Linux)
32