mzbac commited on
Commit
32101cb
1 Parent(s): e9dad46

Update the model type to make it compatible with mlx-lm's model mapping.

Browse files

Once the model type is updated, it should be ready to be ported into mlx-lm and able to be lora fine-tuned with gate.

Files changed (1) hide show
  1. config.json +1 -1
config.json CHANGED
@@ -16,7 +16,7 @@
16
  "img_processor": null,
17
  "initializer_range": 0.02,
18
  "layer_norm_epsilon": 1e-05,
19
- "model_type": "phi-msft",
20
  "n_embd": 2560,
21
  "n_head": 32,
22
  "n_head_kv": null,
 
16
  "img_processor": null,
17
  "initializer_range": 0.02,
18
  "layer_norm_epsilon": 1e-05,
19
+ "model_type": "phixtral",
20
  "n_embd": 2560,
21
  "n_head": 32,
22
  "n_head_kv": null,