Instructions to use digitous/Javelin-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digitous/Javelin-R with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="digitous/Javelin-R")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("digitous/Javelin-R") model = AutoModelForCausalLM.from_pretrained("digitous/Javelin-R") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use digitous/Javelin-R with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "digitous/Javelin-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/Javelin-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/digitous/Javelin-R
- SGLang
How to use digitous/Javelin-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/Javelin-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/Javelin-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/Javelin-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/Javelin-R", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use digitous/Javelin-R with Docker Model Runner:
docker model run hf.co/digitous/Javelin-R
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,10 @@ license: creativeml-openrail-m
|
|
| 5 |
Javelin-R is a penta merge of KoboldAI's GPT-J classics;
|
| 6 |
|
| 7 |
((Janeway + Shinen) + (Adventure + Skein)) + GPT-R.
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
| 9 |
GPT-R itself is a 60/40 merge of two instruct research models (see digitous/GPT-R for full credits).
|
| 10 |
|
| 11 |
This 5x+ merge is not intended for minors, as it can produce NC-17+ content (mostly from Shinen).
|
|
@@ -17,6 +20,6 @@ through the use of weight sum merge technology.
|
|
| 17 |
Mileage mat vary. No refunds best wishes.
|
| 18 |
Mainly intended to be utilized with Open
|
| 19 |
Source KoboldAI software. Optimal sampler
|
| 20 |
-
and settings not determined.
|
| 21 |
|
| 22 |
https://github.com/KoboldAI/KoboldAI-Client
|
|
|
|
| 5 |
Javelin-R is a penta merge of KoboldAI's GPT-J classics;
|
| 6 |
|
| 7 |
((Janeway + Shinen) + (Adventure + Skein)) + GPT-R.
|
| 8 |
+
|
| 9 |
+
Janeway + Shinen is listed under JANIN-GPTJ.
|
| 10 |
+
Adventure + Skein is listed under Adventien-GPTJ.
|
| 11 |
+
|
| 12 |
GPT-R itself is a 60/40 merge of two instruct research models (see digitous/GPT-R for full credits).
|
| 13 |
|
| 14 |
This 5x+ merge is not intended for minors, as it can produce NC-17+ content (mostly from Shinen).
|
|
|
|
| 20 |
Mileage mat vary. No refunds best wishes.
|
| 21 |
Mainly intended to be utilized with Open
|
| 22 |
Source KoboldAI software. Optimal sampler
|
| 23 |
+
and settings not determined. Feedback Welcome!
|
| 24 |
|
| 25 |
https://github.com/KoboldAI/KoboldAI-Client
|