Upload AuriStream checkpoint

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+tags:
+- audio
+- speech
+- language-model
+- auristream
+library_name: transformers
+---
+
+# AuriStream100M_80Pred_BigAudioDataset_500k
+
+**AuriStream** is a speech language model by **Greta Tuckute** and **Klemen Kotar**.
+
+This model predicts cochlear tokens from a tokenizer such as [WavCochCausalV8192](https://huggingface.co/TuKoResearch/WavCochCausalV8192).
+
+
+
+## Model Details
+
+| Parameter | Value |
+|-----------|-------|
+| Parameters | ~0.59B |
+| Layers | 12 |
+| Hidden Size | 768 |
+| Attention Heads | 12 |
+| Vocab Size | 8192 |
+| Prediction Steps | 80 |
+
+## Usage
+
+```python
+from transformers import AutoModel, AutoConfig
+
+# Load with trust_remote_code for custom model
+model = AutoModel.from_pretrained(
+    "TuKoResearch/AuriStream100M_80Pred_BigAudioDataset_500k",
+    trust_remote_code=True,
+)
+
+# Or load config first
+config = AutoConfig.from_pretrained("TuKoResearch/AuriStream100M_80Pred_BigAudioDataset_500k", trust_remote_code=True)
+```
+
+## Base Model Code
+
+This checkpoint uses shared model code from [TuKoResearch/AuriStream-base](https://huggingface.co/TuKoResearch/AuriStream-base).
+
+## Tokenizer
+
+This model uses cochlear tokens from [WavCochCausalV8192](https://huggingface.co/TuKoResearch/WavCochCausalV8192).

config.json

@@ -0,0 +1,21 @@
+{
+  "model_type": "AuriStream",
+  "architectures": [
+    "AuriStreamModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "TuKoResearch/AuriStream-base--configuration_auristream.AuriStreamConfig",
+    "AutoModel": "TuKoResearch/AuriStream-base--modeling_auristream.AuriStreamModel",
+    "AutoModelForCausalLM": "TuKoResearch/AuriStream-base--modeling_auristream.AuriStreamModel"
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "vocab_size": 8192,
+  "n_embd": 768,
+  "n_layer": 12,
+  "n_head": 12,
+  "n_pred_steps": 80,
+  "dropout": 0.0,
+  "bias": false,
+  "input_conv_kernel_size": 0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1898aee0a328d275a67806ac74c0f0b1edb250e3073c85393c13f6104a9084
+size 2378264656