metadata
license: apache-2.0
language:
- ar
- zh
- en
base_model: FreedomIntelligence/AceGPT-v2-32B-Chat
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
FreedomIntelligence/AceGPT-v2-32B-Chat - GGUF
This repo contains GGUF format model files for FreedomIntelligence/AceGPT-v2-32B-Chat.
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 |
|---|---|---|---|
| AceGPT-v2-32B-Chat-Q2_K.gguf | Q2_K | 11.384 GB | smallest, significant quality loss - not recommended for most purposes |
| AceGPT-v2-32B-Chat-Q3_K_S.gguf | Q3_K_S | 13.304 GB | very small, high quality loss |
| AceGPT-v2-32B-Chat-Q3_K_M.gguf | Q3_K_M | 14.730 GB | very small, high quality loss |
| AceGPT-v2-32B-Chat-Q3_K_L.gguf | Q3_K_L | 15.943 GB | small, substantial quality loss |
| AceGPT-v2-32B-Chat-Q4_0.gguf | Q4_0 | 17.229 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| AceGPT-v2-32B-Chat-Q4_K_S.gguf | Q4_K_S | 17.363 GB | small, greater quality loss |
| AceGPT-v2-32B-Chat-Q4_K_M.gguf | Q4_K_M | 18.347 GB | medium, balanced quality - recommended |
| AceGPT-v2-32B-Chat-Q5_0.gguf | Q5_0 | 20.924 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| AceGPT-v2-32B-Chat-Q5_K_S.gguf | Q5_K_S | 20.924 GB | large, low quality loss - recommended |
| AceGPT-v2-32B-Chat-Q5_K_M.gguf | Q5_K_M | 21.499 GB | large, very low quality loss - recommended |
| AceGPT-v2-32B-Chat-Q6_K.gguf | Q6_K | 24.849 GB | very large, extremely low quality loss |
| AceGPT-v2-32B-Chat-Q8_0.gguf | Q8_0 | 32.182 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/AceGPT-v2-32B-Chat-GGUF --include "AceGPT-v2-32B-Chat-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/AceGPT-v2-32B-Chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'