ShellWhisperer 1.5B | Sweet Tea StudioShellWhisperer 1.5B
Natural language → precise bash commands. Tiny, fast, uncensored.
Verified source
Kindtext-generationBase modelQwen2.5Versionv5521c340a32127482d46575efa611e7bb4ac24d0Licenseapache-2.0PublisherFableforge AiCgrade
Model source
- Kind
- text-generation
- Base model
- Qwen2.5
- Version
- v5521c340a32127482d46575efa611e7bb4ac24d0
- License
- apache-2.0
- Publisher
- Fableforge Ai
- Parameters
- 5B
- Tasks
- text-generation
- Source
- Hugging Face
--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: text-generation tags: - 1.5b - commands - devops - fableforge - gguf - imatrix - llama.cpp - lm-studio - ollama - shell - sysadmin - terminal - text-generation - uncensored --- # ShellWhisperer-1.5B > **Natural language → precise bash commands. Tiny, fast, uncensored.** [](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B) [](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus) Base model: [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) · Part of the **FableForge** ecosystem. --- ## ⚡ Quickest start — Ollama (these pulls credit the source, not a mirror) ```bash ollama run hf.co/fableforge-ai/ShellWhisperer-1.5B:Q4_K_M ``` ## 🦙 llama.cpp ```bash llama-cli -hf fableforge-ai/ShellWhisperer-1.5B:Q4_K_M -p "Hello!" ``` ## 💠 LM Studio Search **`fableforge-ai/ShellWhisperer-1.5B`** and pick a quant below. --- ## 📦 Provided quants (download one file, not the whole repo) | File | Quant | Size | Notes | | ---- | ----- | ---- | ----- | | [shellwhisperer-1.5b-f16.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-f16.gguf) | `F16` | 3.09 GB | Full precision (unquantized). Reference / conversion. | | [shellwhisperer-1.5b-Q8_0.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q8_0.gguf) | `Q8_0` | 1.65 GB | Extremely high quality — usually overkill. | | [shellwhisperer-1.5b-Q6_K.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q6_K.gguf) | `Q6_K` | 1.27 GB | Very high quality, near-perfect. **Recommended** if you have the RAM. | | [shellwhisperer-1.5b-Q5_K_M.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q5_K_M.gguf) | `Q5_K_M` | 1.13 GB | High quality. **Recommended.** | | [shellwhisperer-1.5b-Q4_K_M.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q4_K_M.gguf) | `Q4_K_M` | 0.99 GB | ⭐ **Best size/quality balance — default pick for most users.** | | [shellwhisperer-1.5b-IQ4_XS.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-IQ4_XS.gguf) | `IQ4_XS` | 0.90 GB | imatrix — great quality, smaller than Q4_K_S. **Recommended for low RAM.** | | [shellwhisperer-1.5b-Q4_0.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q4_0.gguf) | `Q4_0` | 0.93 GB | Legacy format — prefer Q4_K_M. | | [shellwhisperer-1.5b-Q3_K_M.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q3_K_M.gguf) | `Q3_K_M` | 0.82 GB | Lower quality; usable when RAM is tight. | | [shellwhisperer-1.5b-IQ3_XXS.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-IQ3_XXS.gguf) | `IQ3_XXS` | 0.67 GB | imatrix very low quality. | | [shellwhisperer-1.5b-Q2_K.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-Q2_K.gguf) | `Q2_K` | 0.68 GB | Very low quality — surprisingly usable. | | [shellwhisperer-1.5b-IQ2_XXS.gguf](https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B/blob/main/shellwhisperer-1.5b-IQ2_XXS.gguf) | `IQ2_XXS` | 0.51 GB | Tiny imatrix — last resort. | **Not sure?** Take **`Q4_K_M`**. Low RAM → **`IQ4_XS`**. Max quality → **`Q6_K`**. ## 🧠 Prompt format (ChatML) ``` system {system_prompt} user {prompt} assistant ``` ## 🌌 See it live — the FableForge demos This family powers a galaxy of free, interactive HF Spaces: - 🧭 [FableForge Nexus](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus) - 🍺 [Infinite NPC](https://huggingface.co/spaces/fableforge-ai/infinite-npc) - 🎭 [Dual-GM](https://huggingface.co/spaces/King3Djbl/dual-gm-simulator) - 💻 [ShellWhisperer](https://huggingface.co/spaces/King3Djbl/shellwhisperer-terminal) - 👻 [Ghost Writer](https://huggingface.co/spaces/fableforge-ai/ghost-writer) ## Citation ```bibtex @misc{shellwhisperer1.5b2024, title={ShellWhisperer-1.5B: Agent Orchestration via Fine-Tuned Language Models}, author={FableForge Team}, year={2024}, url={https://huggingface.co/fableforge-ai/ShellWhisperer-1.5B} } ``` --- *⭐ Like & share — it helps people find the source instead of a mirror.*
Sources & provenance
1 active source
Source evidence
3 excerpts
license: apache-2.0 language: en libraryname: transformers pipelinetag: text-generation tags: 1.5b commands devops fableforge gguf imatrix llama.cpp lm-studio ollama shell sysadmin terminal text-generation uncensored
Jul 11
Natural language → precise bash commands. Tiny, fast, uncensored.
fableforge-ai/ShellWhisperer-1.5B