Upload README.md with huggingface_hub
Browse files
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
|
@@ -25,64 +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 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
What is Dolphin?
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
Dolphin 3.0 is the next generation of the Dolphin series of
|
54 |
-
instruct-tuned models. Designed to be the ultimate general purpose
|
55 |
-
local model, enabling coding, math, agentic, function calling, and
|
56 |
-
general use cases.
|
57 |
-
|
58 |
-
|
59 |
-
Dolphin aims to be a general purpose instruct model, similar to the
|
60 |
-
models behind ChatGPT, Claude, Gemini. But these models present
|
61 |
-
problems for businesses seeking to include AI in their products.
|
62 |
-
|
63 |
-
|
64 |
-
They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
|
65 |
-
They maintain control of the model versions, sometimes changing
|
66 |
-
things silently, or deprecating older models that your business relies
|
67 |
-
on.
|
68 |
-
They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
|
69 |
-
They can see all your queries and they can potentially use that data
|
70 |
-
in ways you wouldn't want.
|
71 |
-
Dolphin, in contrast, is steerable and gives control to the system
|
72 |
-
owner. You set the system prompt. You decide the alignment. You have
|
73 |
-
control of your data. Dolphin does not impose its ethics or guidelines
|
74 |
-
on you. You are the one who decides the guidelines.
|
75 |
-
|
76 |
-
|
77 |
-
Dolphin belongs to YOU, it is your tool, an extension of your will.
|
78 |
-
Just as you are personally responsible for what you do with a knife,
|
79 |
-
gun, fire, car, or the internet, you are the creator and originator of
|
80 |
-
any content you generate with Dolphin.
|
81 |
-
|
82 |
-
|
83 |
-
https://erichartford.com/uncensored-models
|
84 |
-
|
85 |
-
---
|
86 |
## Use with llama.cpp
|
87 |
Install llama.cpp through brew (works on Mac and Linux)
|
88 |
|
|
|
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 |
|