metadata
license: mit
language:
- en
base_model: cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
datasets:
- cognitivecomputations/Dolphin-2.9.2
- teknium/OpenHermes-2.5
- m-a-p/CodeFeedback-Filtered-Instruction
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- microsoft/orca-math-word-problems-200k
- internlm/Agent-FLAN
- cognitivecomputations/SystemChat-2.0
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated - GGUF
This repo contains GGUF format model files for cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q2_K.gguf | Q2_K | 4.847 GB | smallest, significant quality loss - not recommended for most purposes |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q3_K_S.gguf | Q3_K_S | 5.648 GB | very small, high quality loss |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q3_K_M.gguf | Q3_K_M | 6.287 GB | very small, high quality loss |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q3_K_L.gguf | Q3_K_L | 6.844 GB | small, substantial quality loss |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_0.gguf | Q4_0 | 7.355 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_S.gguf | Q4_K_S | 7.411 GB | small, greater quality loss |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M.gguf | Q4_K_M | 7.827 GB | medium, balanced quality - recommended |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q5_0.gguf | Q5_0 | 8.961 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q5_K_S.gguf | Q5_K_S | 8.961 GB | large, low quality loss - recommended |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q5_K_M.gguf | Q5_K_M | 9.204 GB | large, very low quality loss - recommended |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q6_K.gguf | Q6_K | 10.667 GB | very large, extremely low quality loss |
| dolphin-2.9.2-Phi-3-Medium-abliterated-Q8_0.gguf | Q8_0 | 13.816 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/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF --include "dolphin-2.9.2-Phi-3-Medium-abliterated-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/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'