Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 19
How to use bazwyn/Stage1-12B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="bazwyn/Stage1-12B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("bazwyn/Stage1-12B")
model = AutoModelForCausalLM.from_pretrained("bazwyn/Stage1-12B")How to use bazwyn/Stage1-12B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bazwyn/Stage1-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "bazwyn/Stage1-12B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/bazwyn/Stage1-12B
How to use bazwyn/Stage1-12B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "bazwyn/Stage1-12B" \
--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": "bazwyn/Stage1-12B",
"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 "bazwyn/Stage1-12B" \
--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": "bazwyn/Stage1-12B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use bazwyn/Stage1-12B with Docker Model Runner:
docker model run hf.co/bazwyn/Stage1-12B
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using TheDrummer/Rocinante-12B-v1.1 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: anthracite-org/magnum-v4-12b
parameters:
density: 0.3
weight: 0.3
- model: TheDrummer/Rocinante-12B-v1.1
parameters:
density: 0.7
weight: 0.5
- model: VongolaChouko/Starcannon-Unleashed-12B-v1.0
parameters:
density: 0.1
weight: 0.2
merge_method: ties
base_model: TheDrummer/Rocinante-12B-v1.1
parameters:
normalize: true
int8_mask: true
dtype: bfloat16