Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
kenhktsui/nano-phi-115M-v0.1 - GGUF
This repo contains GGUF format model files for kenhktsui/nano-phi-115M-v0.1.
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 |
---|---|---|---|
nano-phi-115M-v0.1-Q2_K.gguf | Q2_K | 0.061 GB | smallest, significant quality loss - not recommended for most purposes |
nano-phi-115M-v0.1-Q3_K_S.gguf | Q3_K_S | 0.067 GB | very small, high quality loss |
nano-phi-115M-v0.1-Q3_K_M.gguf | Q3_K_M | 0.069 GB | very small, high quality loss |
nano-phi-115M-v0.1-Q3_K_L.gguf | Q3_K_L | 0.072 GB | small, substantial quality loss |
nano-phi-115M-v0.1-Q4_0.gguf | Q4_0 | 0.077 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
nano-phi-115M-v0.1-Q4_K_S.gguf | Q4_K_S | 0.077 GB | small, greater quality loss |
nano-phi-115M-v0.1-Q4_K_M.gguf | Q4_K_M | 0.078 GB | medium, balanced quality - recommended |
nano-phi-115M-v0.1-Q5_0.gguf | Q5_0 | 0.086 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
nano-phi-115M-v0.1-Q5_K_S.gguf | Q5_K_S | 0.086 GB | large, low quality loss - recommended |
nano-phi-115M-v0.1-Q5_K_M.gguf | Q5_K_M | 0.087 GB | large, very low quality loss - recommended |
nano-phi-115M-v0.1-Q6_K.gguf | Q6_K | 0.096 GB | very large, extremely low quality loss |
nano-phi-115M-v0.1-Q8_0.gguf | Q8_0 | 0.124 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/nano-phi-115M-v0.1-GGUF --include "nano-phi-115M-v0.1-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/nano-phi-115M-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 122
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.
Model tree for tensorblock/nano-phi-115M-v0.1-GGUF
Base model
kenhktsui/nano-phi-115M-v0.1Datasets used to train tensorblock/nano-phi-115M-v0.1-GGUF
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard21.930
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard27.860
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard25.340
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard46.000
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard50.830
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000