Downloads · 30 days
166
14% of all-time downloads
barbarabhb/nl2sh-qwen3.5-2b-GGUF
nl2sh-qwen3.5-2b-GGUF is a text generation model from barbarabhb. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Natural-language → shell command generator, trained as a drop-in alternative to whatisit-nl2sh's nl2sh-1.5b (Qwen2.5-Coder-1.5B base). This one uses Qwen3.5-2B (hybrid linear-attention text backbone, vision tower remo…
Downloads · 30 days
166
14% of all-time downloads
All-time downloads
1.2K
Public
Repo size
23.5 GB
Likes
1
Public
Click a slice to open those files.
.gguf16.5 GB · 98%
From the Hugging Face model README
Natural-language → shell command generator, trained as a drop-in alternative to
whatisit-nl2sh's nl2sh-1.5b (Qwen2.5-Coder-1.5B base).
This one uses Qwen3.5-2B (hybrid linear-attention text backbone, vision tower removed for export)
and the same benchmark family for training data.
Ask in plain English:
Q: find files bigger than 100MB in this folder
A: find . -size +100M
Q: list all running docker containers
A: docker ps
Q: watch memory usage update every second
A: watch -n 1 top -b
| file | size | use |
|---|---|---|
nl2sh-qwen35-q4_k_m.gguf | 1.2G | default pick — smallest practical |
nl2sh-qwen35-q6_k.gguf | 1.5G | better — statistically indistinguishable from f16 |
nl2sh-qwen35-q8_0.gguf | 1.9G | near-lossless (+0.07% ppl) |
nl2sh-qwen35-bf16.gguf | 3.6G | full precision reference |
nl2sh-qwen35-q4_k_m_imx.gguf | 1.2G | Q4_K_M with imatrix (imatrix.gguf) |
imatrix.gguf | 1.9M | importance matrix, corpus = NL2SH-ALFA nl/bash pairs |
lora-adapter/ | 179M | PEFT LoRA adapter used for training |
Recommendation: Q4_K_M if you want the small file (matches what upstream ships at a similar size class);
Q6_K is the sweet spot and costs only +300 MB; Q8_0 if you want effectively zero quantization loss.
| variant | PPL | Δ vs f16 |
|---|---|---|
| f16 | 4.8921 | — |
| bf16 | 4.8919 | −0.00% |
| Q8_0 | 4.8957 | +0.07% |
| Q6_K | 4.9007 | +0.18% |
| Q4_K_M + imatrix | 5.0082 | +2.37% |
| Q4_K_M | 5.0765 | +3.77% |
Greedy-decoding spot checks (16 fixed prompts): Q8_0 matched f16 on 13/16, Q6_K 12/16, Q4_K_M 9/16 — most differences were equivalent commands rather than errors.
Reproducing/forking the upstream recipe, adapted:
| Base | Qwen3.5-2B (text backbone; vision tower + MTP stripped at export) |
| Data | NL2SH-ALFA train split, 40,639 NL/command pairs (chat format) |
| LoRA rank / alpha / dropout | 32 / 64 / 0.05 |
| Target modules | all linear (incl. GDN linear-attention projections) |
| LR / schedule | 2e-4, cosine, 3% warmup |
| Epochs | 2, packing off |
| Batch | 16 x 2 grad accum (effective 32), seq len 512 |
| Loss | assistant-only (chat-template masked) |
| Precision / seed | bf16, seed 42 |
| Hardware | one RX 9070 XT (gfx1201), ~1h14m |
Final: eval_loss 0.4257, eval token accuracy 87.6%.
Note for RDNA4/ROCm trainers: training required
PYTORCH_HIP_ALLOC_CONF=roundup_power2_divisions:16 and packing disabled to avoid the
gfx1201 hipBLASLt page-fault bug (ROCm#6600).
llama-server -m nl2sh-qwen35-q4_k_m.gguf --jinja --temp 0
whatisit setup --model ./nl2sh-qwen35-q4_k_m.gguf
whatisit doctor
Generation expects the model's chat template with thinking disabled
(enable_thinking=false → empty <think></think> block, handled automatically by the template).
Greedy decoding (temperature 0), output capped around 64 tokens — it answers with one command.
InterCode-ALFA (300 tasks, temp 0, max_tokens 64) results will be filled in after the harness run.
| model | pass rate |
|---|---|
| GPT-4o (published) | 0.73 |
| nl2sh-3b (upstream) | 0.657 |
| nl2sh-1.5b (upstream, default) | 0.620 |
| this model | pending |