Downloads · 30 days
24
22% of all-time downloads
code-ministry-ltd/librarian-curator-qwen35-9b-harvesting
librarian-curator-qwen35-9b-harvesting is a text generation model from code-ministry-ltd. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A rank-8 LoRA adapter that teaches Qwen3.5-9B to run The Librarian's harvesting job: picking durable facts out of a settled conversation transcript and turning them into candidate memories worth keeping.
Downloads · 30 days
24
22% of all-time downloads
All-time downloads
109
Public
Repo size
107 MB
Likes
0
Public
Click a slice to open those files.
.safetensors58.2 MB · 54%
From the Hugging Face model README
A rank-8 LoRA adapter that teaches Qwen3.5-9B to run The Librarian's harvesting job: picking durable facts out of a settled conversation transcript and turning them into candidate memories worth keeping.
The Librarian is an open-source durable-memory layer for coding agents
(code-ministry-ltd/the-librarian). Its curator runs three jobs — harvesting,
intake, and grooming — each with its own job section of one unified prompt.
This adapter was trained for the harvesting job only.
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
base = "unsloth/Qwen3.5-9B"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="cuda")
model = PeftModel.from_pretrained(model, "code-ministry-ltd/librarian-curator-qwen35-9b-harvesting")
This repo also ships the adapter as a GGUF LoRA
(curator-qwen35-9b-harvesting-100-r8-lora-f16.gguf, f16). Load it on any
Qwen3.5-9B GGUF (Q8_0 recommended) — the scale is 1.0 by design:
llama-server -m Qwen3.5-9B-Q8_0.gguf \
--lora-scaled curator-qwen35-9b-harvesting-100-r8-lora-f16.gguf:1.0 \
--jinja --chat-template-file <qwen3.5 chat template> \
--chat-template-kwargs '{"enable_thinking": false}'
Point your curator's harvesting model config at this adapter (e.g. via the per-job model settings added in the curator unification, spec 043). Leave intake/grooming on the base model or their own adapters.
Adapter weights: Apache-2.0 (matching the base model). Training data was private and is not redistributed.