metadata
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- manu/project_gutenberg
tags:
- TensorBlock
- GGUF
base_model: amd/AMD-Llama-135m
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
amd/AMD-Llama-135m - GGUF
This repo contains GGUF format model files for amd/AMD-Llama-135m.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| AMD-Llama-135m-Q2_K.gguf | Q2_K | 0.056 GB | smallest, significant quality loss - not recommended for most purposes |
| AMD-Llama-135m-Q3_K_S.gguf | Q3_K_S | 0.063 GB | very small, high quality loss |
| AMD-Llama-135m-Q3_K_M.gguf | Q3_K_M | 0.068 GB | very small, high quality loss |
| AMD-Llama-135m-Q3_K_L.gguf | Q3_K_L | 0.071 GB | small, substantial quality loss |
| AMD-Llama-135m-Q4_0.gguf | Q4_0 | 0.077 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| AMD-Llama-135m-Q4_K_S.gguf | Q4_K_S | 0.077 GB | small, greater quality loss |
| AMD-Llama-135m-Q4_K_M.gguf | Q4_K_M | 0.080 GB | medium, balanced quality - recommended |
| AMD-Llama-135m-Q5_0.gguf | Q5_0 | 0.090 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| AMD-Llama-135m-Q5_K_S.gguf | Q5_K_S | 0.090 GB | large, low quality loss - recommended |
| AMD-Llama-135m-Q5_K_M.gguf | Q5_K_M | 0.091 GB | large, very low quality loss - recommended |
| AMD-Llama-135m-Q6_K.gguf | Q6_K | 0.103 GB | very large, extremely low quality loss |
| AMD-Llama-135m-Q8_0.gguf | Q8_0 | 0.133 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/AMD-Llama-135m-GGUF --include "AMD-Llama-135m-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/AMD-Llama-135m-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'