Upload folder using huggingface_hub (#1)

- e597aa14ee005e5ce7fd8f5d952cbcc9dae1a699ec8316bdd67c63ca4f2c19e6 (8579d979c882c6dce126d3a5be33d995172dcd12)

README.md

@@ -0,0 +1 @@
+[Google's Flan-T5 medium](https://huggingface.co/google/flan-t5-small) converted to [MLX](https://github.com/ml-explore/mlx-examples) format and quantized up to 4 bits with group size 64.

config.json

@@ -0,0 +1,28 @@
+{
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dropout_rate": 0.1,
+    "eos_token_id": 1,
+    "feed_forward_proj": "gated-gelu",
+    "initializer_factor": 1.0,
+    "is_encoder_decoder": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "n_positions": 512,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "output_past": true,
+    "pad_token_id": 0,
+    "quantization": {
+        "bits": 4,
+        "group_size": 64
+    },
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75b02a2239442889c89aded9c3e79ed99589fdb1496c3dad5f3bb1cf919dc3a
+size 238255725

weights.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84485e228c1c4f4a0c76b3b219a9a7fd68022797957b3f9e823e21d0fff7843d
+size 238399972