Total runs:
275.3K
Run Growth:
259.1K
Growth Rate:
94.11%
Sponsored by
ThumbnailCreator.com
kai-os / Carnice-V2-27b
Model's Last Updated: April 26 2026
image-text-to-text
Introduction of Carnice-V2-27b
Model Details of Carnice-V2-27b
Carnice-V2-27B for Hermes Agent
Carnice-V2-27B is a full merged BF16 SFT of
Qwen/Qwen3.6-27B
for Hermes-style agent traces. This repository contains the standalone merged model weights, not only a LoRA adapter.
Benchmarks
| Metric | Qwen3.6-27B base | Carnice SFT |
|---|---|---|
| IFEval prompt strict, limit 20 | 85.0% | 90.0% |
| IFEval prompt loose, limit 20 | 85.0% | 90.0% |
| IFEval instruction strict, limit 20 | 90.0% | 93.3% |
| IFEval instruction loose, limit 20 | 90.0% | 93.3% |
| Held-out assistant-token eval loss | 0.607 | 0.414 |
| Held-out assistant-token eval perplexity | 1.835 | 1.513 |
The benchmark artifact bundle is included under
benchmarks/
. It contains the rendered graph, extracted
metrics.json
, benchmark scripts, and raw result files used to make the chart.
Scope note: the IFEval run is a short
limit=20
A/B smoke benchmark, not an official full leaderboard score. Held-out loss/perplexity is the exact assistant-only training-format validation metric from the SFT script. The raw BFCL two-case smoke files are included for auditability, but they are too small to use as a model-quality claim.
Training
This checkpoint was produced from the recovered 8K split-window Carnice run:
| Item | Value |
|---|---|
| Base model |
Qwen/Qwen3.6-27B
|
| SFT framework | Unsloth/PEFT LoRA, then merged to BF16 safetensors |
| Loss mask | Assistant-token-only |
| Context/windowing | 8,192 token windows with 1,024 token overlap |
| Train rows before windowing | 3,473 |
| Train windows | 6,554 |
| Eval examples | 110 |
| Source mix | 1,508 Carnice rows, 1,015 DJLougen Hermes rows, 950 Lambda GLM-5.1 Hermes rows |
Usage
import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer
model_id = "kai-os/carnice-v2-27b"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
model_id,
dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
This is intended for agentic Hermes-style use. Validate with your own agent harness before relying on it for production behavior.
Runs of kai-os Carnice-V2-27b on huggingface.co
121
Total runs
0
24-hour runs
3
3-day runs
2
7-day runs
-612
30-day runs
More Information About Carnice-V2-27b huggingface.co Model
Url of Carnice-V2-27b
Carnice-V2-27b huggingface.co Url
Provider of Carnice-V2-27b huggingface.co
Other API from kai-os
Updated:April 26 2026
Total runs:
48
Run Growth:
23
Growth Rate:
47.92%
Total runs:
44
Run Growth:
39
Growth Rate:
88.64%
Total runs:
30
Run Growth:
-55
Growth Rate:
-183.33%