Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: l3utterfly/minima-3b-layla-v2
|
3 |
+
inference: false
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
license: llama2
|
7 |
+
model_creator: l3utterfly
|
8 |
+
model_name: minima-3b-layla-v2
|
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 |
+
# l3utterfly/minima-3b-layla-v2-GGUF
|
23 |
+
|
24 |
+
Quantized GGUF model files for [minima-3b-layla-v2](https://huggingface.co/l3utterfly/minima-3b-layla-v2) from [l3utterfly](https://huggingface.co/l3utterfly)
|
25 |
+
|
26 |
+
|
27 |
+
| Name | Quant method | Size |
|
28 |
+
| ---- | ---- | ---- |
|
29 |
+
| [minima-3b-layla-v2.fp16.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.fp16.gguf) | fp16 | 6.04 GB |
|
30 |
+
| [minima-3b-layla-v2.q2_k.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q2_k.gguf) | q2_k | 1.30 GB |
|
31 |
+
| [minima-3b-layla-v2.q3_k_m.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q3_k_m.gguf) | q3_k_m | 1.51 GB |
|
32 |
+
| [minima-3b-layla-v2.q4_k_m.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q4_k_m.gguf) | q4_k_m | 1.85 GB |
|
33 |
+
| [minima-3b-layla-v2.q5_k_m.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q5_k_m.gguf) | q5_k_m | 2.15 GB |
|
34 |
+
| [minima-3b-layla-v2.q6_k.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q6_k.gguf) | q6_k | 2.48 GB |
|
35 |
+
| [minima-3b-layla-v2.q8_0.gguf](https://huggingface.co/afrideva/minima-3b-layla-v2-GGUF/resolve/main/minima-3b-layla-v2.q8_0.gguf) | q8_0 | 3.21 GB |
|
36 |
+
|
37 |
+
|
38 |
+
|
39 |
+
## Original Model Card:
|
40 |
+
# Model Card
|
41 |
+
|
42 |
+
### Model Description
|
43 |
+
|
44 |
+
[MiniMA-3B](https://huggingface.co/GeneZC/MiniMA-3B) (from GeneZC) fine-tuned by:
|
45 |
+
1. Teatime Roleplay dataset for text completion
|
46 |
+
2. ShareGPT datasets for multi-turn conversations.
|
47 |
+
|
48 |
+
- **Developed by:** l3utterfly
|
49 |
+
- **Funded by:** Layla Network
|
50 |
+
- **Model type:** Llama2
|
51 |
+
- **Language(s) (NLP):** English
|
52 |
+
- **License:** Llama2
|
53 |
+
- **Finetuned from model:** MiniMA-3B
|
54 |
+
|
55 |
+
## Uses
|
56 |
+
|
57 |
+
Base model used by Layla - the offline personal assistant: https://www.layla-network.ai
|
58 |
+
|
59 |
+
Help & support: https://discord.gg/x546YJ6nYC
|
60 |
+
|
61 |
+
Prompt:
|
62 |
+
```
|
63 |
+
USER:
|
64 |
+
ASSISTANT:
|
65 |
+
```
|
66 |
+
|
67 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|