Model Overview
Model Features
Model Capabilities
Use Cases
đ Pygmalion 2 7B - GGUF
This repository provides GGUF format model files for Pygmalion 2 7B, a text generation model. It details the model's characteristics, compatibility, and how to download and use it.
đ Quick Start
This repo offers GGUF format model files for PygmalionAI's Pygmalion 2 7B.

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
- Model creator: PygmalionAI
- Original model: Pygmalion 2 7B
⨠Features
- Text Generation: Capable of generating text based on given prompts.
- Custom Prompt Template: Uses a custom prompt template with
<|system|>
,<|user|>
and<|model|>
tokens for multi - role interactions. - Multiple Quantization Methods: Offers various quantization methods for different use cases and hardware requirements.
đĻ Installation
How to download GGUF files
Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
- LM Studio
- LoLLMS Web UI
- Faraday.dev
In text-generation-webui
Under Download Model, you can enter the model repo: TheBloke/Pygmalion-2-7B-GGUF and below it, a specific filename to download, such as: pygmalion-2-7b.q4_K_M.gguf. Then click Download.
On the command line, including multiple files at once
I recommend using the huggingface-hub
Python library:
pip3 install huggingface-hub>=0.17.1
Then you can download any individual model file to the current directory, at high speed, with a command like this:
huggingface-cli download TheBloke/Pygmalion-2-7B-GGUF pygmalion-2-7b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
More advanced huggingface-cli download usage
You can also download multiple files at once with a pattern:
huggingface-cli download TheBloke/Pygmalion-2-7B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
For more documentation on downloading with huggingface-cli
, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer
:
pip3 install hf_transfer
And set environment variable HF_HUB_ENABLE_HF_TRANSFER
to 1
:
HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Pygmalion-2-7B-GGUF pygmalion-2-7b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
Windows CLI users: Use set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1
before running the download command.
đģ Usage Examples
Example llama.cpp
command
Make sure you are using llama.cpp
from commit d0cee0d36d5be95a0d9088b674dbb27354107221 or later.
./main -ngl 32 -m pygmalion-2-7b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows: {{persona}}. You shall reply to the user while staying in character, and generate long responses."
đ Documentation
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It also supports metadata, and is designed to be extensible.
Here is an incomplete list of clients and libraries that are known to support GGUF:
- llama.cpp. The source project for GGUF. Offers a CLI and a server option.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
- LM Studio, an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
- llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
Prompt template: Custom
The model has been trained on prompts using three different roles, which are denoted by the following tokens: <|system|>
, <|user|>
and <|model|>
.
The <|system|>
prompt can be used to inject out-of-channel information behind the scenes, while the <|user|>
prompt should be used to indicate user input. The <|model|>
token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
The system prompt has been designed to allow the model to "enter" various modes and dictate the reply length. Here's an example:
<|system|>Enter RP mode. Pretend to be {{char}} whose persona follows:
{{persona}}
You shall reply to the user while staying in character, and generate long responses.
Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d36d5be95a0d9088b674dbb27354107221
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
Explanation of quantisation methods
Click to see details
The new methods available are:
- GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
- GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
- GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
- GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
- GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
Provided files
Name | Quant method | Bits | Size | Max RAM required | Use case |
---|---|---|---|---|---|
pygmalion-2-7b.Q2_K.gguf | Q2_K | 2 | 2.83 GB | 5.33 GB | smallest, significant quality loss - not recommended for most purposes |
pygmalion-2-7b.Q3_K_S.gguf | Q3_K_S | 3 | 2.95 GB | 5.45 GB | very small, high quality loss |
pygmalion-2-7b.Q3_K_M.gguf | Q3_K_M | 3 | 3.30 GB | 5.80 GB | very small, high quality loss |
pygmalion-2-7b.Q3_K_L.gguf | Q3_K_L | 3 | 3.60 GB | 6.10 GB | small, substantial quality loss |
pygmalion-2-7b.Q4_0.gguf | Q4_0 | 4 | 3.83 GB | 6.33 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
pygmalion-2-7b.Q4_K_S.gguf | Q4_K_S | 4 | 3.86 GB | 6.36 GB | small, greater quality loss |
pygmalion-2-7b.Q4_K_M.gguf | Q4_K_M | 4 | 4.08 GB | 6.58 GB | medium, balanced quality - recommended |
pygmalion-2-7b.Q5_0.gguf | Q5_0 | 5 | 4.65 GB | 7.15 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
pygmalion-2-7b.Q5_K_S.gguf | Q5_K_S | 5 | 4.65 GB | 7.15 GB | large, low quality loss - recommended |
pygmalion-2-7b.Q5_K_M.gguf | Q5_K_M | 5 | 4.78 GB | 7.28 GB | large, very low quality loss - recommended |
pygmalion-2-7b.Q6_K.gguf | Q6_K | 6 | 5.53 GB | 8.03 GB | very large, extremely low quality loss |
pygmalion-2-7b.Q8_0.gguf | Q8_0 | 8 | 7.16 GB | 9.66 GB | very large, extremely low quality loss - not recommended |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
Repositories available
- AWQ model(s) for GPU inference.
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- PygmalionAI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
đ License
The model is licensed under llama2.
Property | Details |
---|---|
Model Type | llama |
Training Data | PygmalionAI/PIPPA, Open - Orca/OpenOrca, Norquinal/claude_multiround_chat_30k, jondurbin/airoboros - gpt4 - 1.4.1, databricks/databricks - dolly - 15k |
â ī¸ Important Note
For manual downloaders, you almost never want to clone the entire repo as multiple different quantisation formats are provided, and most users only want to pick and download a single file.
đĄ Usage Tip
When using the
huggingface-cli
to download files, you can use patterns to download multiple files at once. Also, installinghf_transfer
can accelerate downloads on fast connections.

