Add Orpheus full fine-tune weights + base tokenizer

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,29 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- text-to-speech
+- orpheus
+- llama
+base_model: canopylabs/orpheus-3b-0.1-pretrained
+---
+
+# Orpheus full fine-tune (merged weights)
+
+This repository contains **full fine-tuned causal LM weights** from **vaghawan/eng-pigdin-mix-full-ft-mar-29-orpheus** (``checkpoint-1408``),
+packaged with the **tokenizer** from **canopylabs/orpheus-3b-0.1-pretrained** for inference with the Orpheus / SNAC stack.
+
+## Load
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("vaghawan/orpheus-model-full", torch_dtype="auto", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("vaghawan/orpheus-model-full")
+```
+
+## Source
+
+- Weights: [vaghawan/eng-pigdin-mix-full-ft-mar-29-orpheus](https://huggingface.co/vaghawan/eng-pigdin-mix-full-ft-mar-29-orpheus) ``checkpoint-1408``
+- Tokenizer: [canopylabs/orpheus-3b-0.1-pretrained](https://huggingface.co/canopylabs/orpheus-3b-0.1-pretrained)

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "use_cache": false,
+  "vocab_size": 156939
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.4.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b830f288eb005acef3912ced07b2a65289d08c3151b36dbcb7942931b44bf61d
+size 13203485376

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<|audio|>"
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3fecb199b4170636dbfab986d25f628157268d37b861f9cadaca60b1353bce
+size 22849547