Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: TitleOS/RocketZephyr-3b
|
3 |
+
inference: false
|
4 |
+
license: other
|
5 |
+
license_link: LICENSE
|
6 |
+
license_name: stabilityai-non-commerical-license
|
7 |
+
model_creator: TitleOS
|
8 |
+
model_name: RocketZephyr-3b
|
9 |
+
pipeline_tag: text-generation
|
10 |
+
quantized_by: afrideva
|
11 |
+
tags:
|
12 |
+
- gguf
|
13 |
+
- ggml
|
14 |
+
- quantized
|
15 |
+
- q2_k
|
16 |
+
- q3_k_m
|
17 |
+
- q4_k_m
|
18 |
+
- q5_k_m
|
19 |
+
- q6_k
|
20 |
+
- q8_0
|
21 |
+
---
|
22 |
+
# TitleOS/RocketZephyr-3b-GGUF
|
23 |
+
|
24 |
+
Quantized GGUF model files for [RocketZephyr-3b](https://huggingface.co/TitleOS/RocketZephyr-3b) from [TitleOS](https://huggingface.co/TitleOS)
|
25 |
+
|
26 |
+
|
27 |
+
| Name | Quant method | Size |
|
28 |
+
| ---- | ---- | ---- |
|
29 |
+
| [rocketzephyr-3b.fp16.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.fp16.gguf) | fp16 | 5.59 GB |
|
30 |
+
| [rocketzephyr-3b.q2_k.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q2_k.gguf) | q2_k | 1.20 GB |
|
31 |
+
| [rocketzephyr-3b.q3_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q3_k_m.gguf) | q3_k_m | 1.39 GB |
|
32 |
+
| [rocketzephyr-3b.q4_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q4_k_m.gguf) | q4_k_m | 1.71 GB |
|
33 |
+
| [rocketzephyr-3b.q5_k_m.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q5_k_m.gguf) | q5_k_m | 1.99 GB |
|
34 |
+
| [rocketzephyr-3b.q6_k.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q6_k.gguf) | q6_k | 2.30 GB |
|
35 |
+
| [rocketzephyr-3b.q8_0.gguf](https://huggingface.co/afrideva/RocketZephyr-3b-GGUF/resolve/main/rocketzephyr-3b.q8_0.gguf) | q8_0 | 2.97 GB |
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
## Original Model Card:
|
40 |
+
# RocketZephyr-3B
|
41 |
+
|
42 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
43 |
+
|
44 |
+
An attempt at creating a 3B parameter merged model using [StabilityAI's Zephyr-3b](https://huggingface.co/stabilityai/stablelm-zephyr-3b) and [Pansophic's Rocket-3B](https://huggingface.co/pansophic/rocket-3B).
|
45 |
+
|
46 |
+
### Repo Description
|
47 |
+
|
48 |
+
This repo serves as an housing for my experimentation with creating a 3 billion parameter merged model using [mergekit](https://github.com/cg123/mergekit)
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
- **Merged Models:** stabilityai/stablelm-zephyr-3b & pansophic/rocket-3B
|
53 |
+
- **Merge Weights:** 1.0 & 0.3
|
54 |
+
- **Merge Method:** Linear
|
55 |
+
- **License:** I believe this (current) model inherits the Stable Non-Commercial Research Community License Agreement and as such is licensed by it as well.
|