Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
How to use from
SGLangUse 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 "appvoid/v-base" \
--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": "appvoid/v-base",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using appvoid/palmer-003 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: vihangd/DopeyTinyLlama-1.1B-v1
parameters:
density: 0.5
weight: 0.5
- model: raidhon/coven_tiny_1.1b_32k_orpo_alpha
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: appvoid/palmer-003
parameters:
normalize: false
int8_mask: true
dtype: float16
- Downloads last month
- 4
Model tree for appvoid/v-base
Merge model
this model
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "appvoid/v-base" \ --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": "appvoid/v-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'