Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 19
How to use kainatq/KPT-7B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="kainatq/KPT-7B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("kainatq/KPT-7B")
model = AutoModelForCausalLM.from_pretrained("kainatq/KPT-7B", device_map="auto")How to use kainatq/KPT-7B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kainatq/KPT-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/KPT-7B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/kainatq/KPT-7B
How to use kainatq/KPT-7B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "kainatq/KPT-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/KPT-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/KPT-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/KPT-7B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use kainatq/KPT-7B with Docker Model Runner:
docker model run hf.co/kainatq/KPT-7B
thanks to mradermacher for creating gguf variants of my model. get it here mradermacher/KPT-7B-GGUF
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using kainatq/kainaticulous-rp-7b-v0.2 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: kainatq/kainaticulous-rp-7b-v0.2
#no parameters necessary for base model
- model: ResplendentAI/Aura_v3_7B
parameters:
density: 0.6
weight: 0.25
- model: ResplendentAI/DaturaCookie_7B
parameters:
density: 0.6
weight: 0.25
- model: ResplendentAI/Asherah_7B
parameters:
density: 0.6
weight: 0.25
- model: ResplendentAI/Persephone_7B
parameters:
density: 0.6
weight: 0.25
merge_method: ties
base_model: kainatq/kainaticulous-rp-7b-v0.2
parameters:
normalize: false
int8_mask: true
dtype: float16