update to new format

README.md

@@ -26,7 +26,7 @@ export HF_HUB_ENABLE_HF_TRANSFER=1
 huggingface-cli download --local-dir Llama-2-7b-mlx mlx-llama/Llama-2-7b-mlx
 
 # Run example
-python mlx-examples/llama/llama.py Llama-2-7b-mlx/llama-2-7b.npz Llama-2-7b-mlx/tokenizer.model "My name is "
+python mlx-examples/llama/llama.py Llama-2-7b-mlx/ Llama-2-7b-chat-mlx/tokenizer.model "My name is "
 ```
 
 Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b/tree/main) for details on Llama 2.

params.json

@@ -0,0 +1 @@
+{"dim": 4096, "multiple_of": 256, "n_heads": 32, "n_layers": 32, "norm_eps": 1e-05, "vocab_size": -1}

llama-2-7b.npz → weights.npz

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972e4c45b030eb2f71b1335c484f029c0844011c07c725130dddbc06b67b4b49
-size 13476918398
+oid sha256:626b9b6158cc36a3eec08eec6e4cca444d76ece81ec3dd820f3c954037e398c9
+size 13476919308