ReasonCritic 7B

--- license: apache-2.0 language: - en library_name: transformers pipeline_tag: text-generation base_model: ableforge-ai/ReasonCritic-7B base_model_relation: finetune tags: - chain-of-thought - critic - evaluation - fableforge - gguf - imatrix - llama.cpp - lm-studio - ollama - reasoning - text-generation --- # ReasonCritic-7B > **A reasoning critic — evaluates and improves chain-of-thought.** [](https://huggingface.co/fableforge-ai/ReasonCritic-7B) [](https://huggingface.co/spaces/fableforge-ai/fableforge-nexus) Base model: [fableforge-ai/ReasonCritic-7B](https://huggingface.co/fableforge-ai/ReasonCritic-7B) · Part of the **FableForge** ecosystem. --- ## ⚡ Quickest start — Ollama (these pulls credit the source, not a mirror) ```bash ollama run hf.co/fableforge-ai/ReasonCritic-7B:Q4_K_M ``` ## 🦙 llama.cpp ```bash llama-cli -hf fableforge-ai/ReasonCritic-7B:Q4_K_M -p "Hello!" ``` ## 💠 LM Studio Search **`fableforge-ai/ReasonCritic-7B`** and pick a quant below. --- ## 📦 Provided quants (download one file, not the whole repo) | File | Quant | Size | Notes | | ---- | ----- | ---- | ----- | | [reasoncritic-7b.F16.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.F16.gguf) | `F16` | 14.43 GB | Full precision (unquantized). Reference / conversion. | | [reasoncritic-7b.Q8_0.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q8_0.gguf) | `Q8_0` | 8.71 GB | Extremely high quality — usually overkill. | | [reasoncritic-7b.Q6_K.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q6_K.gguf) | `Q6_K` | 6.73 GB | Very high quality, near-perfect. **Recommended** if you have the RAM. | | [reasoncritic-7b.Q5_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q5_K_M.gguf) | `Q5_K_M` | 5.85 GB | High quality. **Recommended.** | | [reasoncritic-7b.Q4_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q4_K_M.gguf) | `Q4_K_M` | 5.03 GB | ⭐ **Best size/quality balance — default pick for most users.** | | [reasoncritic-7b.Q4_0.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q4_0.gguf) | `Q4_0` | 4.77 GB | Legacy format — prefer Q4_K_M. | | [reasoncritic-7b.Q3_K_M.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q3_K_M.gguf) | `Q3_K_M` | 4.12 GB | Lower quality; usable when RAM is tight. | | [reasoncritic-7b.Q2_K.gguf](https://huggingface.co/fableforge-ai/ReasonCritic-7B/blob/main/reasoncritic-7b.Q2_K.gguf) | `Q2_K` | 3.28 GB | Very low quality — surprisingly usable. | **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) --- *⭐ Like & share — it helps people find the source instead of a mirror.*