Instructions to use Bytes512/Waterbuck with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bytes512/Waterbuck with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Bytes512/Waterbuck")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Bytes512/Waterbuck") model = AutoModelForCausalLM.from_pretrained("Bytes512/Waterbuck", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Bytes512/Waterbuck with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Bytes512/Waterbuck" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bytes512/Waterbuck", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Bytes512/Waterbuck
- SGLang
How to use Bytes512/Waterbuck 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 "Bytes512/Waterbuck" \ --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": "Bytes512/Waterbuck", "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 "Bytes512/Waterbuck" \ --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": "Bytes512/Waterbuck", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Bytes512/Waterbuck with Docker Model Runner:
docker model run hf.co/Bytes512/Waterbuck
metadata
base_model:
- Heralax/Augmental-13b-v1.50_B
- ChaiML/season_4_top_solution
- NeverSleep/Noromaid-13b-v0.3
- TheBloke/Llama-2-13B-fp16
- Fredithefish/RP_Base
tags:
- mergekit
- merge
waterbuck
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DARE TIES merge method using TheBloke/Llama-2-13B-fp16 as a base.
Models Merged
The following models were included in the merge:
- Heralax/Augmental-13b-v1.50_B
- ChaiML/season_4_top_solution
- NeverSleep/Noromaid-13b-v0.3
- Fredithefish/RP_Base
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Heralax/Augmental-13b-v1.50_B
parameters:
density: 0.5
weight: 0.3
- model: Fredithefish/RP_Base
parameters:
density: 0.5
weight: 0.6
- model: NeverSleep/Noromaid-13b-v0.3
parameters:
density: 0.5
weight: 0.5
- model: ChaiML/season_4_top_solution
parameters:
density: 0.5
weight: 0.5
base_model: TheBloke/Llama-2-13B-fp16
merge_method: dare_ties
parameters:
normalize: 1.0