Downloads · 30 days
20
14% of all-time downloads
rhoahndur/retrosynthesis-qwen3-4b-gguf
retrosynthesis-qwen3-4b-gguf is a machine learning model from rhoahndur. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Q4KM quantized version of rhoahndur/retrosynthesis-qwen3-4b for CPU inference via llama.cpp.
Downloads · 30 days
20
14% of all-time downloads
All-time downloads
144
Public
Repo size
2.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.5 GB · 100%
From the Hugging Face model README
Q4_K_M quantized version of rhoahndur/retrosynthesis-qwen3-4b for CPU inference via llama.cpp.
Size: 2.5 GB Quantization: Q4_K_M
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="rhoahndur/retrosynthesis-qwen3-4b-gguf",
filename="retrosynthesis-qwen3-4b-Q4_K_M.gguf",
n_ctx=512,
)
output = llm.create_chat_completion(
messages=[
{"role": "system", "content": "You are a retrosynthesis expert. Output ONLY reactant SMILES separated by dots."},
{"role": "user", "content": "Predict the reactants for: CC(=O)Oc1ccccc1C(=O)O"}
],
max_tokens=256,
temperature=0.7,
)
print(output["choices"][0]["message"]["content"])