Downloads · 30 days
38
19% of all-time downloads
Shayde182/rhymeai-qwen3.5-4B-gguf
rhymeai-qwen3.5-4B-gguf is a machine learning model from Shayde182. 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.
RhymeAI's lyric-assistant fine-tune of Qwen/Qwen3.5-4B (QLoRA r=16/alpha=16, 2 epochs, 6,572 verified examples covering line suggestions, passage rewrites, single-word rewrites, and synonyms).
Downloads · 30 days
38
19% of all-time downloads
All-time downloads
197
Public
Repo size
2.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.7 GB · 95%
From the Hugging Face model README
RhymeAI's lyric-assistant fine-tune of Qwen/Qwen3.5-4B (QLoRA r=16/alpha=16, 2 epochs, 6,572 verified examples covering line suggestions, passage rewrites, single-word rewrites, and synonyms).
Status: experimental — not the shipped app model. On RhymeAI's 43-case format harness this model sweeps: 100% format pass on all four tasks and 99% rhyme hit (3-run medians), beating the shipped Gemma 4 E4B fine-tune, in a 2.5 GB artifact. It was retired after a blind paired naturalness A/B (60 pairs, third-party judge, position-bias controlled) where the Gemma E4B fine-tune won on lyric craft 37-15 (p = 0.0032). Shipped models live in Shayde182/rhymeai-gemma-4-gguf.
| File | What |
|---|---|
qwen3.5-4B-rhymeai-Q4_K_M.gguf | Merged + quantized model for llama.cpp (2.5 GB) |
adapter/ | The LoRA adapter (PEFT safetensors, r=16) |
metrics.json | Training metrics (Colab L4, val loss 1.543 -> 1.508) |
The model was trained on — and must be prompted with — the raw ChatML
no-think surface form, posted to llama.cpp /completion with stop
<|im_end|>:
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>
</think>
Sampler contract: temp 0.8, top-k 40, top-p 0.95, ctx 2048.
llama.cpp's convert_lora_to_gguf.py cannot convert LoRA factors for this
architecture (the V-head reorder has no LoRA-factor equivalent), and a plain
PEFT merge drops the MTP draft layer, yielding a GGUF llama.cpp rejects.
This artifact was produced by: PEFT merge -> convert_hf_to_gguf.py ->
grafting the stock GGUF's metadata over the tuned tensors -> llama-quantize.