Model Stock: All we need is just a few fine-tuned models
Paper • 2403.19522 • Published • 15
How to use kainatq/KPRA-7b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="kainatq/KPRA-7b") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kainatq/KPRA-7b")
model = AutoModelForCausalLM.from_pretrained("kainatq/KPRA-7b")How to use kainatq/KPRA-7b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kainatq/KPRA-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "kainatq/KPRA-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/kainatq/KPRA-7b
How to use kainatq/KPRA-7b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "kainatq/KPRA-7b" \
--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": "kainatq/KPRA-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "kainatq/KPRA-7b" \
--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": "kainatq/KPRA-7b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use kainatq/KPRA-7b with Docker Model Runner:
docker model run hf.co/kainatq/KPRA-7b
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using kainatq/Kainoverse-7b-v0.1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: model_stock
base_model: kainatq/Kainoverse-7b-v0.1
parameters:
models:
- model: ResplendentAI/DaturaCookie_7B
- model: icefog72/IceDrunkenCherryRP-7b
- model: ChaoticNeutrals/RP_Vision_7B
- model: Endevor/InfinityRP-v1-7B
- model: MaziyarPanahi/Synatra-7B-v0.3-RP-Mistral-7B-Instruct-v0.2-slerp
- model: icefog72/IceCocoaRP-7b
dtype: bfloat16