Instructions to use NeverSleep/Nethena-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NeverSleep/Nethena-13B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NeverSleep/Nethena-13B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Nethena-13B") model = AutoModelForCausalLM.from_pretrained("NeverSleep/Nethena-13B") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NeverSleep/Nethena-13B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NeverSleep/Nethena-13B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeverSleep/Nethena-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NeverSleep/Nethena-13B
- SGLang
How to use NeverSleep/Nethena-13B 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 "NeverSleep/Nethena-13B" \ --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": "NeverSleep/Nethena-13B", "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 "NeverSleep/Nethena-13B" \ --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": "NeverSleep/Nethena-13B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NeverSleep/Nethena-13B with Docker Model Runner:
docker model run hf.co/NeverSleep/Nethena-13B
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ Nethena-13B model. Use Alpaca format. Suitable for RP, ERP and general stuff.
|
|
| 10 |
|
| 11 |
What would happen if we combine all of out best models? Well.. here it is, the holy grail: **Echidna v0.3** + **Athena v3** + **Nete**
|
| 12 |
|
|
|
|
| 13 |
|
| 14 |
[Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
|
| 15 |
|
|
@@ -18,7 +19,7 @@ What would happen if we combine all of out best models? Well.. here it is, the h
|
|
| 18 |
|
| 19 |
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
|
| 20 |
|
| 21 |
-
This repo contains
|
| 22 |
|
| 23 |
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Nethena-13B)
|
| 24 |
|
|
|
|
| 10 |
|
| 11 |
What would happen if we combine all of out best models? Well.. here it is, the holy grail: **Echidna v0.3** + **Athena v3** + **Nete**
|
| 12 |
|
| 13 |
+
This model also has a 20b version, you can check it out right [here](https://huggingface.co/NeverSleep/Nethena-20B).
|
| 14 |
|
| 15 |
[Recommended settings - No settings yet(Please suggest some over in the Community tab!)]
|
| 16 |
|
|
|
|
| 19 |
|
| 20 |
<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
|
| 21 |
|
| 22 |
+
This repo contains fp16 files of Nethena-13B.
|
| 23 |
|
| 24 |
[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Nethena-13B)
|
| 25 |
|