CoolFace
Modelpublic

Snapkitty/snapkitty-merged

sourceHugging Faceotherupdated 19d agoView on Hugging Face
0likes39downloads
Model Card

snapkitty-merged — Nemotron 4.2B Merged Q4KM

Merged and fine-tuned Nemotron Mini 4.2B, quantized to Q4KM GGUF.

Model Details

PropertyValue
ArchitectureNemotron
Parameters4.2B
QuantizationQ4KM
Context Length4096
Embedding Dim3072
Layers32
Attention Heads24 (8 KV)
Vocab Size256,000
File Size~2.6 GB

Usage

Ollama

bash
ollama run hf.co/Snapkitty/snapkitty-merged:Q4_K_M

llama.cpp

bash
llama-cli -m snapkitty-merged.Q4_K_M.gguf -p "Your prompt here"

Python (llama-cpp-python)

python
from llama_cpp import Llama
llm = Llama.from_pretrained(
    repo_id="Snapkitty/snapkitty-merged",
    filename="snapkitty-merged.Q4_K_M.gguf",
)
output = llm("Your prompt here", max_tokens=512)
print(output["choices"][0]["text"])

Links