Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: minchyeom/Starlette-1-3B
|
3 |
+
pipeline_tag: text-generation
|
4 |
+
inference: true
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
license: llama3.2
|
8 |
+
model_creator: minchyeom
|
9 |
+
model_name: Starlette-1-3B
|
10 |
+
model_type: llama
|
11 |
+
quantized_by: brittlewis12
|
12 |
+
tags:
|
13 |
+
- reasoning
|
14 |
+
- llama
|
15 |
+
- llama3.2
|
16 |
+
|
17 |
+
---
|
18 |
+
|
19 |
+
# Starlette 1 3B GGUF
|
20 |
+
|
21 |
+
**Original model**: [Starlette-1-3B](https://huggingface.co/minchyeom/Starlette-1-3B)
|
22 |
+
|
23 |
+
**Model creator**: [minchyeom](https://huggingface.co/minchyeom)
|
24 |
+
|
25 |
+
> Shows excellent reasoning capabilities across a wide range of domains.
|
26 |
+
|
27 |
+
> This is meant to be used with JSON structured output with the following columns: reasoning and output.
|
28 |
+
|
29 |
+
This repo contains GGUF format model files for minchyeom’s Starlette 1 3B.
|
30 |
+
|
31 |
+
### What is GGUF?
|
32 |
+
|
33 |
+
GGUF is a file format for representing AI models. It is the third version of the format,
|
34 |
+
introduced by the llama.cpp team on August 21st 2023.
|
35 |
+
|
36 |
+
Converted with llama.cpp build 4730 (revision [fe163d5](https://github.com/ggerganov/llama.cpp/commits/fe163d5bf3fb8e99c96ff6d21775fa3d1daee3cf)),
|
37 |
+
using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs).
|
38 |
+
|
39 |
+
### Prompt template: Llama 3 Chat
|
40 |
+
|
41 |
+
```
|
42 |
+
<|start_header_id|>system<|end_header_id|>
|
43 |
+
|
44 |
+
{{system_prompt}}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
45 |
+
|
46 |
+
{{prompt}}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
47 |
+
|
48 |
+
|
49 |
+
```
|
50 |
+
|
51 |
+
#### Recommended System Prompt
|
52 |
+
|
53 |
+
```
|
54 |
+
You are Starlette, a curious human being.
|
55 |
+
```
|
56 |
+
|
57 |
+
---
|
58 |
+
|
59 |
+
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!
|
60 |
+
|
61 |
+

|
62 |
+
|
63 |
+
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
|
64 |
+
- create & save **Characters** with custom system prompts & temperature settings
|
65 |
+
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
|
66 |
+
* or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
|
67 |
+
- make it your own with custom **Theme colors**
|
68 |
+
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!
|
69 |
+
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
|
70 |
+
* if you **already have the app**, download Starlette now!
|
71 |
+
* <cnvrsai:///models/search/hf?id=brittlewis12/Starlette-1-3B-GGUF>
|
72 |
+
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date
|
73 |
+
|