Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,100 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: gemma
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
datasets:
|
| 4 |
+
- NbAiLab/aurora-sft-2512-filtered
|
| 5 |
+
language:
|
| 6 |
+
- 'no'
|
| 7 |
+
- nb
|
| 8 |
+
- nn
|
| 9 |
+
base_model: NbAiLab/borealis-12b-instruct-preview
|
| 10 |
+
pipeline_tag: image-text-to-text
|
| 11 |
+
library_name: transformers
|
| 12 |
+
tags:
|
| 13 |
+
- conversational
|
| 14 |
+
- instruct
|
| 15 |
+
- experimental
|
| 16 |
+
- llama-cpp
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# borealis-12b-instruct-preview
|
| 20 |
+
**Model creator:** [NbAiLab](https://huggingface.co/NbAiLab)<br/>
|
| 21 |
+
**Original model**: [NbAiLab/borealis-12b-instruct-preview](https://huggingface.co/NbAiLab/borealis-12b-instruct-preview)<br/>
|
| 22 |
+
**GGUF quantization:** provided by [NbAiLab](https://huggingface.co/NbAiLab) using `llama.cpp`<br/>
|
| 23 |
+
|
| 24 |
+
## Available Quantizations
|
| 25 |
+
- Q4_K_M
|
| 26 |
+
- Q8_0
|
| 27 |
+
- BF16
|
| 28 |
+
|
| 29 |
+
## Special thanks
|
| 30 |
+
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
|
| 31 |
+
|
| 32 |
+
## Usage Examples
|
| 33 |
+
|
| 34 |
+
### Q4_K_M
|
| 35 |
+
|
| 36 |
+
**Ollama:**
|
| 37 |
+
```bash
|
| 38 |
+
ollama run "hf.co/NbAiLab/borealis-12b-instruct-preview-gguf:Q4_K_M"
|
| 39 |
+
```
|
| 40 |
+
|
| 41 |
+
**LM Studio:**
|
| 42 |
+
```bash
|
| 43 |
+
lms load "NbAiLab/borealis-12b-instruct-preview-gguf/borealis-12b-instruct-preview-Q4_K_M.gguf"
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
**llama.cpp CLI:**
|
| 47 |
+
```bash
|
| 48 |
+
llama-cli --hf "NbAiLab/borealis-12b-instruct-preview-gguf:Q4_K_M" -p "The meaning to life and the universe is"
|
| 49 |
+
```
|
| 50 |
+
|
| 51 |
+
**llama.cpp Server:**
|
| 52 |
+
```bash
|
| 53 |
+
llama-server --hf "NbAiLab/borealis-12b-instruct-preview-gguf:Q4_K_M" -c 4096
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Q8_0
|
| 58 |
+
|
| 59 |
+
**Ollama:**
|
| 60 |
+
```bash
|
| 61 |
+
ollama run "hf.co/NbAiLab/borealis-12b-instruct-preview-gguf:Q8_0"
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
**LM Studio:**
|
| 65 |
+
```bash
|
| 66 |
+
lms load "NbAiLab/borealis-12b-instruct-preview-gguf/borealis-12b-instruct-preview-Q8_0.gguf"
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
**llama.cpp CLI:**
|
| 70 |
+
```bash
|
| 71 |
+
llama-cli --hf "NbAiLab/borealis-12b-instruct-preview-gguf:Q8_0" -p "The meaning to life and the universe is"
|
| 72 |
+
```
|
| 73 |
+
|
| 74 |
+
**llama.cpp Server:**
|
| 75 |
+
```bash
|
| 76 |
+
llama-server --hf "NbAiLab/borealis-12b-instruct-preview-gguf:Q8_0" -c 4096
|
| 77 |
+
```
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
### BF16
|
| 81 |
+
|
| 82 |
+
**Ollama:**
|
| 83 |
+
```bash
|
| 84 |
+
ollama run "hf.co/NbAiLab/borealis-12b-instruct-preview-gguf:BF16"
|
| 85 |
+
```
|
| 86 |
+
|
| 87 |
+
**LM Studio:**
|
| 88 |
+
```bash
|
| 89 |
+
lms load "NbAiLab/borealis-12b-instruct-preview-gguf/borealis-12b-instruct-preview-BF16.gguf"
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
**llama.cpp CLI:**
|
| 93 |
+
```bash
|
| 94 |
+
llama-cli --hf "NbAiLab/borealis-12b-instruct-preview-gguf:BF16" -p "The meaning to life and the universe is"
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
**llama.cpp Server:**
|
| 98 |
+
```bash
|
| 99 |
+
llama-server --hf "NbAiLab/borealis-12b-instruct-preview-gguf:BF16" -c 4096
|
| 100 |
+
```
|