jaredpalmer/Kev 0.5B

• License: Apache-2.0
• Release date: 2026-09-17 (original prototype)
• Modalities: Input: text; Output: typed decisions (choice, score, noul)
• Original model: jaredpalmer/kev-0.5b

Description

Kev reads a document (the state) and typed questions, returning a probability distribution for each question in one forward pass without generating text. The original prototype uses a LoRA adapter and a pointer head on Qwen2.5-0.5B. The upstream model card marks it as superseded by the newer Kev family.

Run

self serve kev:0.5b

Here is a link to the API docs: Decision API.

Example Request

With the server running, open another terminal and send a request:

curl http://localhost:8080/v1/systemone \
	-H 'Content-Type: application/json' \
	-d '{
		"state": "I was charged twice for the same order.",
		"questions": {
			"department": {
				"type": "choice",
				"instructions": "Which department should handle this support ticket?",
				"criteria": {
					"billing": "Payments and refunds",
					"technical": "Technical problems"
				}
			}
		}
	}'

The server returns a JSON decision for the department question.

Engine Parameters

Served by the upstream laya daemon through the ggmlc-laya adapter.

Parameter	Default	What it controls
threads	4	Number of CPU workers; accepts integers from 1 to 1024.
cuda_graph	true for auto / CUDA devices; otherwise false	Capture a CUDA graph for the live request shape.

Override startup settings with --set <parameter>=<value>.

Quantizations and Files

Default variant: q4. Sizes and SHA-256 hashes are pinned in the model registry.

q4 (default)

File	Role	Size	SHA-256	Origin
kev_0.5b_ud_q4_k_m.gguf	model	544.5 MiB (570955168 bytes)	154db89455fb1871b93e4343a2954331c2469d718426c893b4d1bd6f0e1b40bf	mys/kev-0.5b-GGUF

Total download: 544.5 MiB.

q8

File	Role	Size	SHA-256	Origin
kev_0.5b_q8_0.gguf	model	522.8 MiB (548153728 bytes)	5c747e0da78745e49609d6989a0964ce1688fa4741a49ae13f17256acda13280	mys/kev-0.5b-GGUF

Total download: 522.8 MiB.

fp16

File	Role	Size	SHA-256	Origin
kev_0.5b_f16.gguf	model	964.8 MiB (1011668480 bytes)	06d9735d7adfa71b0bad812a712f18d56fc6e8c0b1761d9898561d5110c2470d	mys/kev-0.5b-GGUF

Total download: 964.8 MiB.

Notes

• Text only; up to 16 options per question.
• Context and option limits are compiled into the GGUF and cannot be changed at runtime.
• Download size is not the total runtime memory requirement.
• Origin links use main because these registry entries pin hashes, not repository revisions.

Quality benchmarks

Hugging Face model-card evaluations: Publisher-reported

jaredpalmer/kev-0.5b

Publisher-reported upstream checkpoint; not an independent rank or local quantization

Checked 2026-10-13

Dataset	Metric	Score
held-out split of the six training sources (1,350 questions)	accuracy	0.80
held-out split of the six training sources (1,350 questions)	ECE (10 bins)	0.07
held-out split of the six training sources (1,350 questions)	ECE after temperature scaling (T=1.47)	0.03

Benchmarks

No submitted benchmark reports yet.