Instructions to use lewisdog/lfm2.5-350m-cogs-ask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lewisdog/lfm2.5-350m-cogs-ask with Transformers:

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

pipe = pipeline("text-generation", model="lewisdog/lfm2.5-350m-cogs-ask")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lewisdog/lfm2.5-350m-cogs-ask")
model = AutoModelForCausalLM.from_pretrained("lewisdog/lfm2.5-350m-cogs-ask")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lewisdog/lfm2.5-350m-cogs-ask with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lewisdog/lfm2.5-350m-cogs-ask"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewisdog/lfm2.5-350m-cogs-ask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lewisdog/lfm2.5-350m-cogs-ask

SGLang

How to use lewisdog/lfm2.5-350m-cogs-ask 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 "lewisdog/lfm2.5-350m-cogs-ask" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewisdog/lfm2.5-350m-cogs-ask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lewisdog/lfm2.5-350m-cogs-ask" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lewisdog/lfm2.5-350m-cogs-ask",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lewisdog/lfm2.5-350m-cogs-ask with Docker Model Runner:
```
docker model run hf.co/lewisdog/lfm2.5-350m-cogs-ask
```

lfm2.5-350m-cogs-ask

A 350M ask student for Cogitarium retrieval-QA. Two tasks:

decompose: split a question into 1-4 retrieval sub-questions → {"subquestions":[...]}
synth: answer strictly from provided wiki notes with inline [note-id] citations → {"answer","citations","abstained"}

Trained on the real cogs serialization — slash note-ids (concepts/planner) and [[wikilinks]] in note bodies — plus frontier-teacher-distilled grounded Q&A generated over the real vault. Correct on the deployment distribution; needs no serving hacks.

Serving pins

temperature 0, repeat_penalty 1.0.
Emits exact slash note-ids and handles [[wikilinks]] in bodies natively — you do NOT need to strip wikilinks or fuzzy-match citations (both were required by the earlier hyphen-id variant). Feed evidence as `### [note-id] Title` exactly as `cogs ask` builds it.
Gate abstention upstream. The abstained flag is only moderately reliable; decide "is this answerable?" from retrieval score / the decompose step and don't depend on the field.

Eval (real vault serialization; grounded citation validity)

Distilled from ~600 frontier-teacher-generated grounded Q&A over the real vault (plus the re-serialized base set). Grounded-citation validity:

set	decompose	grounded exact	grounded lenient	abstain
deployment vault (aoa, notes seen in training)	100%	89%	89%	6/11
out-of-domain (unseen clusters)	100%	58%	65%	3/5

Progression as teacher data scaled (out-of-domain grounded strict): vault-aligned only 38% → +204 teacher 50% → +570 teacher 58%. On the vault it is actually trained over, grounded citation is ~89%. Data quality/quantity — not model size — was the binding constraint. Feed evidence as `### [note-id] Title

; citations come back as exact slash-ids, no serving hacks. Gate abstention upstream (the abstained` flag is only moderately reliable). A strong fast tier; the Qwen3-1.7B student remains the quality tier.

Recommended quant: Q8_0 (379 MB, 509 tok/s on GB10). decompose is flawless at any quant incl. Q4_K_M (229 MB).

Base model & license

Fine-tuned from LiquidAI/LFM2.5-350M. Use is governed by the LFM Open License v1.0 (lfm1.0) — see the LICENSE in the base repo. This derivative complies with and inherits those terms; attribution to LiquidAI is retained above.

Provenance

LoRA SFT (TRL) on the Cogitarium distillation datasets, DGX Spark (GB10). Full methodology, loss curves, eval harnesses and per-quant results: see the project RESULTS.md. This is the "fast/small tier" of the Cogitarium model picker; the Qwen3-1.7B students remain the quality tier.

Downloads last month: 1,005

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for lewisdog/lfm2.5-350m-cogs-ask

Base model

LiquidAI/LFM2.5-350M-Base

Finetuned

LiquidAI/LFM2.5-350M

Finetuned

(49)

this model