Upload Voxtral Mini 4B Realtime MLX fp16 weights

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,48 @@
+{
+  "model_type": "voxtral_realtime",
+  "decoder": {
+    "dim": 3072,
+    "n_layers": 26,
+    "head_dim": 128,
+    "hidden_dim": 9216,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "vocab_size": 131072,
+    "norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": 8192,
+    "tied_embeddings": true,
+    "ada_rms_norm_t_cond": true,
+    "ada_rms_norm_t_cond_dim": 32
+  },
+  "encoder_args": {
+    "audio_encoding_args": {
+      "sampling_rate": 16000,
+      "frame_rate": 12.5,
+      "num_mel_bins": 128,
+      "hop_length": 160,
+      "window_size": 400,
+      "chunk_length_s": null,
+      "global_log_mel_max": 1.5,
+      "transcription_format": "streaming"
+    },
+    "dim": 1280,
+    "n_layers": 32,
+    "head_dim": 64,
+    "hidden_dim": 5120,
+    "n_heads": 32,
+    "vocab_size": 131072,
+    "n_kv_heads": 32,
+    "use_biases": true,
+    "use_cache": false,
+    "rope_theta": 1000000.0,
+    "causal": true,
+    "norm_eps": 1e-05,
+    "pos_embed": "rope",
+    "max_source_positions": null,
+    "ffn_type": "swiglu",
+    "norm_type": "rms_norm",
+    "sliding_window": 750,
+    "downsample_factor": 4
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d4ea445ef8787434c82cdc26dfdaf374890da6ae8d30d9fd1eec81719abf37
+size 8870608794

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8434af1d39eba99f0ef46cf1450bf1a63fa941a26933a1ef5dbbf4adf0d00e44
+size 14910348