Instructions to use estrogen/ms24b-exprmerge-v0a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use estrogen/ms24b-exprmerge-v0a with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="estrogen/ms24b-exprmerge-v0a")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("estrogen/ms24b-exprmerge-v0a")
model = AutoModelForCausalLM.from_pretrained("estrogen/ms24b-exprmerge-v0a")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use estrogen/ms24b-exprmerge-v0a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "estrogen/ms24b-exprmerge-v0a"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "estrogen/ms24b-exprmerge-v0a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/estrogen/ms24b-exprmerge-v0a

SGLang

How to use estrogen/ms24b-exprmerge-v0a 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 "estrogen/ms24b-exprmerge-v0a" \
    --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": "estrogen/ms24b-exprmerge-v0a",
		"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 "estrogen/ms24b-exprmerge-v0a" \
        --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": "estrogen/ms24b-exprmerge-v0a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use estrogen/ms24b-exprmerge-v0a with Docker Model Runner:
```
docker model run hf.co/estrogen/ms24b-exprmerge-v0a
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

v0a

This is a merge of pre-trained language models created using mergekitty.

Merge Details

Merge Method

This model was merged using the SCE merge method using unsloth/Mistral-Small-24B-Base-2501 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/Mistral-Small-24B-Base-2501
merge_method: sce
dtype: float32
out_dtype: bfloat16
models:
  - model: allura-org/Mistral-Small-24b-Sertraline-0304
    parameters:
      select_topk: 0.50
  - model: lars1234/Mistral-Small-24B-Instruct-2501-writer
    parameters:
      select_topk: 0.20
  - model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
    parameters:
      select_topk: 0.20
  - model: trashpanda-org/Llama3-24B-Mullein-v1
    parameters:
      select_topk: 0.175
  - model: arcee-ai/Arcee-Blitz
    parameters:
      select_topk: 0.15
  - model: mistralai/Mistral-Small-24B-Instruct-2501
    parameters:
      select_topk: 0.15

# apt install git nano -y
# uv tool install mergekitty --with hf_transfer
# uv tool install https://github.com/aphrodite-engine/aphrodite-engine/releases/download/v0.6.7/aphrodite_engine-0.6.7-cp38-abi3-manylinux1_x86_64.whl --with aphrodite-engine --with setuptools --with hf_transfer
# uv tool install huggingface_hub
# huggingface-cli login
# nano merge.yml
# mergekitty-yaml --cuda --lazy-unpickle merge.yml v0a