You can deploy this model and start earning money today!

Qwen3-4B-slerp

Name: Qwen3-4B-slerp
Availability: InStock

Qwen3-4B-slerp is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

models:
  - model: Loom-Labs/Apollo-1-4B
  - model: NiuTrans/LMT-60-4B-Base
  - model: budecosystem/hex-1
  - model: pixas/Miner-4B
  - model: MegaScience/Qwen3-4B-MegaScience
  - model: spiral-rl/Spiral-Qwen3-4B
  - model: hardlyworking/Sugma4B
  - model: GreenerPastures/Basically-Human-4B
  - model: hardlyworking/AGI
  - model: trollek/MiniButler-4B
  - model: DavidAU/Qwen3-Horror-Instruct-Uncensored-262K-ctx-4B
  - model: minchyeom/Starlette-2-4B
  - model: PJMixers-Dev/Qwen3-Samantha-v0.1-4B

merge_method: multislerp
base_model: Qwen/Qwen3-4B-Base
parameters:
  normalize_weights: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "shashwatmudgal/Qwen3-4B-slerp"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])