lgcharpe commited on
Commit
789672c
·
verified ·
1 Parent(s): fceb25b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -12,6 +12,7 @@ tags:
12
  - conversational
13
  - instruct
14
  - experimental
 
15
  ---
16
 
17
  # Borealis 4B Instruct GGUF (Preview)
@@ -26,8 +27,8 @@ The original model is [NbAiLab/borealis-4b-instruct-preview](https://huggingface
26
  | Model | Bits | Format |
27
  |---|---:|---|
28
  | [NbAiLab/borealis-4b-instruct-preview](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview) | BF16 | Transformers (safetensors) |
 
29
  | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | 8 | GGUF (`q8_0`) |
30
- | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | 16 | GGUF (`f16`) |
31
  | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | BF16 | GGUF (`bf16`) |
32
  | [NbAiLab/borealis-4b-instruct-preview-mlx](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-mlx) | 32 | MLX |
33
- | [NbAiLab/borealis-4b-instruct-preview-mlx-8bits](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-mlx-8bits) | 8 | MLX (quantized) |
 
12
  - conversational
13
  - instruct
14
  - experimental
15
+ pipeline_tag: image-text-to-text
16
  ---
17
 
18
  # Borealis 4B Instruct GGUF (Preview)
 
27
  | Model | Bits | Format |
28
  |---|---:|---|
29
  | [NbAiLab/borealis-4b-instruct-preview](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview) | BF16 | Transformers (safetensors) |
30
+ | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | 4 | GGUF (`q4_K_M`) |
31
  | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | 8 | GGUF (`q8_0`) |
 
32
  | [NbAiLab/borealis-4b-instruct-preview-gguf](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-gguf) | BF16 | GGUF (`bf16`) |
33
  | [NbAiLab/borealis-4b-instruct-preview-mlx](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-mlx) | 32 | MLX |
34
+ | [NbAiLab/borealis-4b-instruct-preview-mlx-8bits](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-mlx-8bits) | 8 | MLX (quantized) |