Instructions to use digitous/Javalion-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/Javalion-R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/Javalion-R")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/Javalion-R") model = AutoModelForCausalLM.from_pretrained("digitous/Javalion-R") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use digitous/Javalion-R with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/Javalion-R" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Javalion-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/Javalion-R
- SGLang
How to use digitous/Javalion-R with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "digitous/Javalion-R" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Javalion-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "digitous/Javalion-R" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "digitous/Javalion-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/Javalion-R with Docker Model Runner:
docker model run hf.co/digitous/Javalion-R
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,12 +6,13 @@ Javalion-R is a penta merge of KoboldAI's GPT-J classics + PygmalionAI's Pygmali
|
|
| 6 |
|
| 7 |
((Janeway + Shinen) + (Skein + Pygmalion)) + GPT-R.
|
| 8 |
|
| 9 |
-
Janeway + Shinen is listed under JANIN-GPTJ. Skein + Pygmalion is listed under
|
| 10 |
|
| 11 |
GPT-R itself is a 60/40 merge of two instruct research models (see digitous/GPT-R for full credits).
|
| 12 |
|
| 13 |
This 5x+ merge is not intended for minors, as it can produce NC-17+ content.
|
| 14 |
|
|
|
|
| 15 |
Javalion-R is a research artefact with dual purpose for entertainment as well as an intended example of potential value instruct can bring when combined with models of a different purpose through the use of weight sum merge technology.
|
| 16 |
|
| 17 |
Mileage mat vary. No refunds best wishes. Mainly intended to be utilized with Open Source KoboldAI software. Optimal sampler and settings not determined. Feedback Welcome!
|
|
|
|
| 6 |
|
| 7 |
((Janeway + Shinen) + (Skein + Pygmalion)) + GPT-R.
|
| 8 |
|
| 9 |
+
Janeway + Shinen is listed under JANIN-GPTJ. Skein + Pygmalion is listed under SKEGMA-GPTJ.
|
| 10 |
|
| 11 |
GPT-R itself is a 60/40 merge of two instruct research models (see digitous/GPT-R for full credits).
|
| 12 |
|
| 13 |
This 5x+ merge is not intended for minors, as it can produce NC-17+ content.
|
| 14 |
|
| 15 |
+
This model differs from Javelin-R by substituting the Adventure model with Pygmalion, as Adventure is rendered redundant in training data by Skein.
|
| 16 |
Javalion-R is a research artefact with dual purpose for entertainment as well as an intended example of potential value instruct can bring when combined with models of a different purpose through the use of weight sum merge technology.
|
| 17 |
|
| 18 |
Mileage mat vary. No refunds best wishes. Mainly intended to be utilized with Open Source KoboldAI software. Optimal sampler and settings not determined. Feedback Welcome!
|