README.md

metadata

datasets:
  - cognitivecomputations/dolphin-r1
  - OpenCoder-LLM/opc-sft-stage1
  - OpenCoder-LLM/opc-sft-stage2
  - microsoft/orca-agentinstruct-1M-v1
  - microsoft/orca-math-word-problems-200k
  - NousResearch/hermes-function-calling-v1
  - AI-MO/NuminaMath-CoT
  - AI-MO/NuminaMath-TIR
  - allenai/tulu-3-sft-mixture
  - cognitivecomputations/dolphin-coder
  - HuggingFaceTB/smoltalk
  - cognitivecomputations/samantha-data
  - m-a-p/CodeFeedback-Filtered-Instruction
  - m-a-p/Code-Feedback
language:
  - en
base_model: cognitivecomputations/Dolphin3.0-R1-Mistral-24B
pipeline_tag: text-generation
library_name: transformers
tags:
  - TensorBlock
  - GGUF

cognitivecomputations/Dolphin3.0-R1-Mistral-24B - GGUF

This repo contains GGUF format model files for cognitivecomputations/Dolphin3.0-R1-Mistral-24B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>

Model file specification

Filename	Quant type	File Size	Description
Dolphin3.0-R1-Mistral-24B-Q2_K.gguf	Q2_K	8.890 GB	smallest, significant quality loss - not recommended for most purposes
Dolphin3.0-R1-Mistral-24B-Q3_K_S.gguf	Q3_K_S	10.400 GB	very small, high quality loss
Dolphin3.0-R1-Mistral-24B-Q3_K_M.gguf	Q3_K_M	11.474 GB	very small, high quality loss
Dolphin3.0-R1-Mistral-24B-Q3_K_L.gguf	Q3_K_L	12.401 GB	small, substantial quality loss
Dolphin3.0-R1-Mistral-24B-Q4_0.gguf	Q4_0	13.442 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Dolphin3.0-R1-Mistral-24B-Q4_K_S.gguf	Q4_K_S	13.549 GB	small, greater quality loss
Dolphin3.0-R1-Mistral-24B-Q4_K_M.gguf	Q4_K_M	14.334 GB	medium, balanced quality - recommended
Dolphin3.0-R1-Mistral-24B-Q5_0.gguf	Q5_0	16.304 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Dolphin3.0-R1-Mistral-24B-Q5_K_S.gguf	Q5_K_S	16.304 GB	large, low quality loss - recommended
Dolphin3.0-R1-Mistral-24B-Q5_K_M.gguf	Q5_K_M	16.764 GB	large, very low quality loss - recommended
Dolphin3.0-R1-Mistral-24B-Q6_K.gguf	Q6_K	19.346 GB	very large, extremely low quality loss
Dolphin3.0-R1-Mistral-24B-Q8_0.gguf	Q8_0	25.055 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Dolphin3.0-R1-Mistral-24B-GGUF --include "Dolphin3.0-R1-Mistral-24B-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Dolphin3.0-R1-Mistral-24B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'