Upload folder using huggingface_hub

README.md

@@ -7,15 +7,15 @@ extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review
   agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
   Face and click below. Requests are processed immediately.
 extra_gated_button_content: Acknowledge license
-base_model: google/gemma-2-2b
 tags:
 - mlx
+base_model: google/gemma-2-9b
 ---
 
 # sigtakahashi/google-de-gozari
 
 The Model [sigtakahashi/google-de-gozari](https://huggingface.co/sigtakahashi/google-de-gozari) was
-converted to MLX format from [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b)
+converted to MLX format from [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b)
 using mlx-lm version **0.20.0**.
 
 ## Use with mlx

config.json

@@ -12,21 +12,30 @@
     "head_dim": 256,
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_activation": "gelu_pytorch_tanh",
-    "hidden_size": 2304,
+    "hidden_size": 3584,
     "initializer_range": 0.02,
-    "intermediate_size": 9216,
+    "intermediate_size": 14336,
     "max_position_embeddings": 8192,
     "model_type": "gemma2",
-    "num_attention_heads": 8,
-    "num_hidden_layers": 26,
-    "num_key_value_heads": 4,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 8,
     "pad_token_id": 0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
     "query_pre_attn_scalar": 256,
     "rms_norm_eps": 1e-06,
     "rope_theta": 10000.0,
     "sliding_window": 4096,
+    "sliding_window_size": 4096,
     "torch_dtype": "float32",
-    "transformers_version": "4.42.4",
+    "transformers_version": "4.42.0.dev0",
     "use_cache": true,
     "vocab_size": 256000
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a7e4142b05d9a2fa92b3f10ed4e2004b246da5fc0749a35f8dfbe5e6e44a29
+size 5199450578