Text-to-Speech
Transformers
Safetensors
English
llama
text-generation
unsloth
text-generation-inference
Instructions to use Gapeleon/Orpheus-4b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gapeleon/Orpheus-4b-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Gapeleon/Orpheus-4b-base")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Gapeleon/Orpheus-4b-base") model = AutoModelForCausalLM.from_pretrained("Gapeleon/Orpheus-4b-base") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use Gapeleon/Orpheus-4b-base with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Gapeleon/Orpheus-4b-base to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Gapeleon/Orpheus-4b-base to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Gapeleon/Orpheus-4b-base to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Gapeleon/Orpheus-4b-base", max_seq_length=2048, )
Delete mergekit_config.yml
Browse filesremove wrong mergekit config
- mergekit_config.yml +0 -26
mergekit_config.yml
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
|
| 2 |
-
dtype: bfloat16
|
| 3 |
-
merge_method: passthrough
|
| 4 |
-
slices:
|
| 5 |
-
# Keep first half intact (layers 0-13)
|
| 6 |
-
- sources:
|
| 7 |
-
- layer_range: [0, 15]
|
| 8 |
-
model: /content/3b_or_base
|
| 9 |
-
|
| 10 |
-
# Duplicate middle section (layers 14-18) with zeroed projections
|
| 11 |
-
- sources:
|
| 12 |
-
- layer_range: [10, 20]
|
| 13 |
-
model: /content/3b_or_base
|
| 14 |
-
parameters:
|
| 15 |
-
scale:
|
| 16 |
-
- filter: o_proj
|
| 17 |
-
value: 0.0
|
| 18 |
-
- filter: down_proj
|
| 19 |
-
value: 0.0
|
| 20 |
-
- value: 1.0
|
| 21 |
-
|
| 22 |
-
# Continue with original layers (14-27 becomes 19-32)
|
| 23 |
-
- sources:
|
| 24 |
-
- layer_range: [16, 27]
|
| 25 |
-
model: /content/3b_or_base
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|