Add files using upload-large-folder tool

.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

README.md

@@ -0,0 +1,42 @@
+---
+library_name: mlx
+language:
+- en
+- fr
+- es
+- de
+- ru
+- zh
+- ja
+- it
+- pt
+- nl
+- ar
+- hi
+- ko
+license: apache-2.0
+inference: false
+base_model: mistralai/Voxtral-Mini-4B-Realtime-2602
+extra_gated_description: If you want to learn more about how we process your personal
+  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+tags:
+- mistral-common
+- mlx
+pipeline_tag: automatic-speech-recognition
+---
+# mlx-community/Voxtral-Mini-4B-Realtime-6bit
+
+This model [mlx-community/Voxtral-Mini-4B-Realtime-6bit](https://huggingface.co/mlx-community/Voxtral-Mini-4B-Realtime-6bit) was converted to MLX format from [mistralai/Voxtral-Mini-4B-Realtime-2602](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602) using [voxmlx](https://github.com/awnihannun/voxmlx).
+
+## Use with voxmlx
+
+```bash
+pip install voxmlx
+```
+
+```python
+from voxmlx import transcribe
+
+text = transcribe("audio.flac", model_path="mlx-community/Voxtral-Mini-4B-Realtime-6bit")
+print(text)
+```

config.json

@@ -0,0 +1,59 @@
+{
+    "ada_rms_norm_t_cond": true,
+    "ada_rms_norm_t_cond_dim": 32,
+    "causal": true,
+    "dim": 3072,
+    "head_dim": 128,
+    "hidden_dim": 9216,
+    "model_max_length": 131072,
+    "model_parallel": 1,
+    "multimodal": {
+        "whisper_model_args": {
+            "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_args": {
+                "downsample_factor": 4
+            }
+        }
+    },
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "n_layers": 26,
+    "norm_eps": 1e-05,
+    "quantization": {
+        "group_size": 64,
+        "bits": 6
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 8192,
+    "tied_embeddings": true,
+    "use_biases": false,
+    "vocab_size": 131072
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b8253dd386a4ce2ac130d937fa4e78ae3332021ad65b8ea1eb5c6c37112319
+size 3609304614

tekken.json

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