moshika-vis-mlx v0.1

Co-authored-by: mboehle <[email protected]>
Co-authored-by: gabrielatkyutail <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,12 @@
+---
+license: cc-by-4.0
+language:
+- en
+base_model:
+- google/paligemma2-3b-pt-448
+- kyutai/moshika-mlx-bf16
+---
+Please refer to the [main model card](https://huggingface.co/kyutai/moshika-vis-pytorch-bf16)
+
+This model page contains the Moshika (female voice) model weights for the `MLX` backend of the MoshiVis repo, 
+in `bfloat16`,`Q8` and `Q4` formats. We provide the same model weights for other backends and quantization formats in the associated model collection.

model.q4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad3780eea1474290a831ef0c04aa20938e98555e3223e55dc0bd1d10d3c7b4c
+size 6541519817

model.q8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b07fb28925b2d7a0ecc84598c9cb7a8207cbe7d16f503f4af0af9814277eb99
+size 10384994661

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31612828132ef75f3f5f9e3f20b61a816f1c06dd0ac4a644333d0cd392d0c21
+size 16614791144

siglip448.config

@@ -0,0 +1 @@
+{"model_type": "siglip_vision_model", "num_hidden_layers": 27, "hidden_size": 1152, "intermediate_size": 4304, "num_attention_heads": 16, "patch_size": 14, "projection_dim": 2304, "image_size": 448, "num_channels": 3, "layer_norm_eps": 1e-06}

tokenizer-e351c8d8-checkpoint125.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b782f0629851a271227fb9d36db65c041790365f11bbe5d3d59369cf863f50
+size 384644900

tokenizer_spm_32k_3.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d4336533ddc26f9acf7250d7fb83492152196c6ea4212c841df76933f18d2d
+size 552778