mlx-community
/

SWE-agent-LM-32B-4bit

Text Generation

software engineering

text-generation-inference

4-bit precision

Model card Files Files and versions

Felladrin commited on 27 days ago

Commit

319e08c

·

verified ·

1 Parent(s): ca11282

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ tags:
 - mlx-my-repo
 ---
-# Felladrin/SWE-agent-LM-32B-mlx-4Bit
-The Model [Felladrin/SWE-agent-LM-32B-mlx-4Bit](https://huggingface.co/Felladrin/SWE-agent-LM-32B-mlx-4Bit) was converted to MLX format from [SWE-bench/SWE-agent-LM-32B](https://huggingface.co/SWE-bench/SWE-agent-LM-32B) using mlx-lm version **0.22.3**.
 ## Use with mlx
@@ -27,7 +27,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
-model, tokenizer = load("Felladrin/SWE-agent-LM-32B-mlx-4Bit")
 prompt="hello"

 - mlx-my-repo
 ---
+# mlx-community/SWE-agent-LM-32B-4bit
+The Model [mlx-community/SWE-agent-LM-32B-4bit](https://huggingface.co/mlx-community/SWE-agent-LM-32B-4bit) was converted to MLX format from [SWE-bench/SWE-agent-LM-32B](https://huggingface.co/SWE-bench/SWE-agent-LM-32B) using mlx-lm version **0.22.3**.
 ## Use with mlx
 ```python
 from mlx_lm import load, generate
+model, tokenizer = load("mlx-community/SWE-agent-LM-32B-4bit")
 prompt="hello"