SAVRN
Search Contact SAVRN

Open-weight model · Text generation

bash2nl-qwen2.5-coder-7b-GGUF

by C. H. Liu C-H-Liu/bash2nl-qwen2.5-coder-7b-GGUF

Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct, merged and quantized to q4KM.

Parameters—
Context—
Weights4.7 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By C. H. Liu, published under apache-2.0, revision fe0d895fa246.

Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct, merged and quantized to q4KM. The Modelfile pins the system prompt and this decoding: 920 held-out commands Judge columns are claude-sonnet-5 scoring a fixed 200-command subset. Apache-2.0, matching the base model, whose weights this GGUF contains. Training data comes from the nl2bash project; consult it for the terms attached to that corpus.

Read C. H. Liu's full model card

bash2nl — Qwen2.5-Coder-7B QLoRA, GGUF q4_K_M

Explains a Bash command line in exactly one English sentence, phrased as an instruction starting with a verb. QLoRA fine-tune of Qwen/Qwen2.5-Coder-7B-Instruct, merged and quantized to q4_K_M.

find . -name "*.py"
-> Display the names of all files in the current directory and recursively into subdirectories with names that end in .py

Usage

hf download C-H-Liu/bash2nl-qwen2.5-coder-7b-GGUF --local-dir bash2nl
cd bash2nl && ollama create bash2nl -f Modelfile
ollama run bash2nl 'ps -ef | grep nginx | awk "{print \$2}" | xargs kill -9'

The Modelfile pins the system prompt and this decoding:

option value
temperature 0.0
top_k 1
top_p 1.0
repeat_penalty 1.0
num_predict 96
num_ctx 4096
stop <|im_end|>, <|endoftext|>

Evaluation

920 held-out commands Judge columns are claude-sonnet-5 scoring a fixed 200-command subset.

metric base + few-shot this model
BLEU 14.59 17.67 33.49
chrF 44.15 45.82 52.21
ROUGE-L 39.09 40.64 53.24
judge acceptable+ 0.880 0.900 0.890
judge wrong 0.120 0.100 0.110
avg words 18.0 17.2 12.4

License

Apache-2.0, matching the base model, whose weights this GGUF contains. Training data comes from the nl2bash project; consult it for the terms attached to that corpus.

Identity and Version

Repository
C-H-Liu/bash2nl-qwen2.5-coder-7b-GGUF
Publisher
C. H. Liu
Task
Text generation
Modality
Text
Library
Not stated by the source
Parameters
Not stated by the source
Languages
en
Revision
fe0d895fa2463c99f6c13ca6f02e6395f32ca332
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

4 files, 4.7 GB in total. The weights are 1 file totalling 4.7 GB in gguf.

Weights1 file · 4.7 GB
Documentation1 file · 1.7 KB
Other1 file · 923 B
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
bash2nl-qwen2.5-coder-7b-qlora-finetuned-q4_k_m.ggufWeights4.7 GB e1efdc3debb3
README.mdDocumentation1.7 KB —
ModelfileOther923 B —
.gitattributesRepository1.6 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
4.7 GB
Download from C. H. Liu

Released by C. H. Liu through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published4.7 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About bash2nl-qwen2.5-coder-7b-GGUF

Can I use bash2nl-qwen2.5-coder-7b-GGUF commercially?

Yes. bash2nl-qwen2.5-coder-7b-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Fine-tune Qwen3 (14B) for free using our Google Colab notebook! - Read our Blog about Qwen3 support: unsloth.ai/blog/qwen3 - View the rest of our notebooks in our docs here. Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: - Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks. - Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding. - Agentic Coding supporting for…

Open weights apache-2.0 transformers
View model

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers
View model

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers
View model

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers
View model

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp
View model