Hugging Face's logo

mlx-community
/
Dolphin3.0-R1-Mistral-24B-4bit

Text Generation
Transformers
Safetensors
MLX
English
mistral
conversational
text-generation-inference
4-bit precision
Model card Files Community
1
abalogh commited on
Commit
6b010e7
·
verified ·
1 Parent(s): 8d891ef

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -23,9 +23,9 @@ tags:
23
  - mlx
24
  ---
25
 
26
- # abalogh/Dolphin3.0-R1-Mistral-24B-4bit
27
 
28
- The Model [abalogh/Dolphin3.0-R1-Mistral-24B-4bit](https://huggingface.co/abalogh/Dolphin3.0-R1-Mistral-24B-4bit) was
29
  converted to MLX format from [cognitivecomputations/Dolphin3.0-R1-Mistral-24B](https://huggingface.co/cognitivecomputations/Dolphin3.0-R1-Mistral-24B)
30
  using mlx-lm version **0.21.4**.
31
 
@@ -38,7 +38,7 @@ pip install mlx-lm
38
  ```python
39
  from mlx_lm import load, generate
40
 
41
- model, tokenizer = load("abalogh/Dolphin3.0-R1-Mistral-24B-4bit")
42
 
43
  prompt = "hello"
44
 
 
23
  - mlx
24
  ---
25
 
26
+ # mlx-community/Dolphin3.0-R1-Mistral-24B-4bit
27
 
28
+ The Model [mlx-community/Dolphin3.0-R1-Mistral-24B-4bit](https://huggingface.co/mlx-community/Dolphin3.0-R1-Mistral-24B-4bit) was
29
  converted to MLX format from [cognitivecomputations/Dolphin3.0-R1-Mistral-24B](https://huggingface.co/cognitivecomputations/Dolphin3.0-R1-Mistral-24B)
30
  using mlx-lm version **0.21.4**.
31
 
 
38
  ```python
39
  from mlx_lm import load, generate
40
 
41
+ model, tokenizer = load("mlx-community/Dolphin3.0-R1-Mistral-24B-4bit")
42
 
43
  prompt = "hello"
44