Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B
|
3 |
+
inference: false
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
license: apache-2.0
|
7 |
+
model_creator: charlesdedampierre
|
8 |
+
model_name: TopicNeuralHermes-2.5-Mistral-7B
|
9 |
+
model_type: mistral
|
10 |
+
pipeline_tag: text-generation
|
11 |
+
prompt_template: |
|
12 |
+
<|im_start|>system
|
13 |
+
{{system_prompt}}<|im_end|>
|
14 |
+
<|im_start|>user
|
15 |
+
{prompt}<|im_end|>
|
16 |
+
<|im_start|>assistant
|
17 |
+
datasets:
|
18 |
+
- bunkalab/topic_based_chatml_dpo_pairs
|
19 |
+
quantized_by: brittlewis12
|
20 |
+
---
|
21 |
+
|
22 |
+
# Beagle14-7B GGUF
|
23 |
+
|
24 |
+
Original model: [TopicNeuralHermes-2.5-Mistral-7B](https://huggingface.co/charlesdedampierre/TopicNeuralHermes-2.5-Mistral-7B)
|
25 |
+
Model creator: [charlesdedampierre](https://huggingface.co/charlesdedampierre)
|
26 |
+
|
27 |
+
This repo contains GGUF format model files for charlesdedampierre’s TopicNeuralHermes-2.5-Mistral-7B.
|
28 |
+
|
29 |
+
> TopicNeuralHermes 2.5 Mistral 7B is a refined model developed through fine-tuning with a specific subset of data, selected via Topic Modeling Techniques using [Bunkatopics](https://github.com/charlesdedampierre/BunkaTopics), as a continuing from [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B).
|
30 |
+
|
31 |
+
> We found the 13 distinctive following topics described by 10 terms each:
|
32 |
+
>
|
33 |
+
> **Emotional Dynamics**: feelings, Quinn, Austin, minority women, teaching, schools, individual, personality, backgrounds, triggers.
|
34 |
+
>
|
35 |
+
> **Global Knowledge Queries**: question, information, geography, news articles, Step, answer, capital city, pipeline system, country, analogy.
|
36 |
+
>
|
37 |
+
> **Digital Interactions and Queries**: questions, question, PersonX, modem, answers, effect relationship, Quora, browser, answer, e-commerce.
|
38 |
+
>
|
39 |
+
> **Business and Cybersecurity**: email, businesses, initiatives, innovation, advertising papers, spam, breaches, antivirus, payments, prospects.
|
40 |
+
>
|
41 |
+
> **Lifestyle and Wellness**: sleep, exercise, gifts, shopping, Casey, stores, stress, headaches, options, mood.
|
42 |
+
>
|
43 |
+
> **Wildlife Ecology**: birds, prey, animals, species, infection, nest, eggs, bacteria, insects, kitty condo.
|
44 |
+
>
|
45 |
+
> **Environmental Science and Climate**: temperature, gases, greenhouse, emissions, perturbation, sulfur, dioxide, climate change, water, heat.
|
46 |
+
>
|
47 |
+
> **Maritime and Mechanical Engineering**: ship, bowling, propulsion, beam width, Filing cabinet, LED, lane, containment area, lawnmower, rotors.
|
48 |
+
>
|
49 |
+
> **Cultural and Social Dynamics**: Lindsey, museum, Kate, Rachel, Jason, Alex, Erin, conversation, Laura, exhibits.
|
50 |
+
>
|
51 |
+
> **Political Media Analysis**: media platforms, election, politics, teenagers, elections, White House, Barack Obama, nation, Confederate, depression.
|
52 |
+
>
|
53 |
+
> **International Relations and Policy**: cooperation, EU, nations, alliance, NATO, European Union, member states, policy, monarch, Brexit.
|
54 |
+
>
|
55 |
+
> **Astrophysics and Physical Sciences**: electrons, km, Moon, acceleration, orbit, friction, current, asteroid, electron, collector emitter.
|
56 |
+
>
|
57 |
+
> **Film Critique and Analysis**: movie review, film, reviewer, sentiment, critic, flaws, DVD, plot, opinion, originality.
|
58 |
+
|
59 |
+
|
60 |
+
### What is GGUF?
|
61 |
+
|
62 |
+
GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
63 |
+
Converted using llama.cpp build 1925 (revision [381ee19](https://github.com/ggerganov/llama.cpp/commit/381ee195721d8e747ee31a60c0751822b3072f02))
|
64 |
+
|
65 |
+
### Prompt template: ChatML
|
66 |
+
|
67 |
+
```
|
68 |
+
<|im_start|>system
|
69 |
+
{{system_message}}<|im_end|>
|
70 |
+
<|im_start|>user
|
71 |
+
{{prompt}}<|im_end|>
|
72 |
+
<|im_start|>assistant
|
73 |
+
```
|
74 |
+
|
75 |
+
---
|
76 |
+
|
77 |
+
## Download & run with [cnvrs](https://testflight.apple.com/join/sFWReS7K) on iPhone, iPad, and Mac!
|
78 |
+
|
79 |
+
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
|
80 |
+
- create & save **Characters** with custom system prompts & temperature settings
|
81 |
+
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
|
82 |
+
- make it your own with custom **Theme colors**
|
83 |
+
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!
|
84 |
+
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
|
85 |
+
|
86 |
+
---
|
87 |
+
|
88 |
+
## Original Model Evaluations:
|
89 |
+
|
90 |
+

|