alvarobartt HF staff commited on
Commit
82087e8
1 Parent(s): abcdd8e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -18,7 +18,7 @@ library_name: mlx
18
 
19
  Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques following a data-first approach. This model is the first version, fine-tuned with DPO on top of [`alignment-handbook/zephyr-7b-sft-full`](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full), which is the SFT model produced to create [`HuggingFaceH4/zephyr-7b-beta`](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta).
20
 
21
- More information at [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1)
22
 
23
  This repository contains the `notus-7b-v1` weights in `npz` format in 4-bit suitable for use with Apple's MLX framework (from 0.6.0 onwards).
24
 
@@ -32,10 +32,10 @@ cd mlx-examples
32
 
33
  # Download model
34
  export HF_HUB_ENABLE_HF_TRANSFER=1
35
- huggingface-cli download --local-dir-use-symlinks False --local-dir notus-7b-v1-4bit alvarobartt/notus-7b-v1-4bit
36
 
37
  # Run example
38
- python llms/mistral/mistral.py --model-path notus-7b-v1-4bit --prompt "My name is"
39
  ```
40
 
41
  Please, refer to the [original model card](https://huggingface.co/argilla/notus-7b-v1) for more details on Notus 7B v1.
 
18
 
19
  Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques following a data-first approach. This model is the first version, fine-tuned with DPO on top of [`alignment-handbook/zephyr-7b-sft-full`](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full), which is the SFT model produced to create [`HuggingFaceH4/zephyr-7b-beta`](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta).
20
 
21
+ More information at [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1).
22
 
23
  This repository contains the `notus-7b-v1` weights in `npz` format in 4-bit suitable for use with Apple's MLX framework (from 0.6.0 onwards).
24
 
 
32
 
33
  # Download model
34
  export HF_HUB_ENABLE_HF_TRANSFER=1
35
+ huggingface-cli download --local-dir-use-symlinks False --local-dir notus-7b-v1-mlx-4bit alvarobartt/notus-7b-v1-mlx-4bit
36
 
37
  # Run example
38
+ python llms/mistral/mistral.py --model-path notus-7b-v1-mlx-4bit --prompt "My name is"
39
  ```
40
 
41
  Please, refer to the [original model card](https://huggingface.co/argilla/notus-7b-v1) for more details on Notus 7B v1.