Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf - GGUF
This repo contains GGUF format model files for openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| openthaigpt-1.0.0-beta-13b-chat-hf-Q2_K.gguf | Q2_K | 4.908 GB | smallest, significant quality loss - not recommended for most purposes |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q3_K_S.gguf | Q3_K_S | 5.717 GB | very small, high quality loss |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q3_K_M.gguf | Q3_K_M | 6.396 GB | very small, high quality loss |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q3_K_L.gguf | Q3_K_L | 6.988 GB | small, substantial quality loss |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q4_0.gguf | Q4_0 | 7.430 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q4_K_S.gguf | Q4_K_S | 7.488 GB | small, greater quality loss |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q4_K_M.gguf | Q4_K_M | 7.931 GB | medium, balanced quality - recommended |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q5_0.gguf | Q5_0 | 9.043 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q5_K_S.gguf | Q5_K_S | 9.043 GB | large, low quality loss - recommended |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q5_K_M.gguf | Q5_K_M | 9.300 GB | large, very low quality loss - recommended |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q6_K.gguf | Q6_K | 10.756 GB | very large, extremely low quality loss |
| openthaigpt-1.0.0-beta-13b-chat-hf-Q8_0.gguf | Q8_0 | 13.930 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/openthaigpt-1.0.0-beta-13b-chat-hf-GGUF --include "openthaigpt-1.0.0-beta-13b-chat-hf-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/openthaigpt-1.0.0-beta-13b-chat-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 184
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.