metadata
library_name: transformers
license: other
base_model: ahmedheakl/asm2asm-deepseek1.3b-xtokenizer-armv8
tags:
- trl
- sft
- generated_from_trainer
- TensorBlock
- GGUF
model-index:
- name: asm2asm-deepseek-1.3b-500k-mac-x86-O0-arm-gnueabi-gcc
results: []
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
ahmedheakl/asm2asm-deepseek1.3b-xtokenizer-armv8 - GGUF
This repo contains GGUF format model files for ahmedheakl/asm2asm-deepseek1.3b-xtokenizer-armv8.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
<｜begin▁of▁sentence｜>{system_prompt}### Instruction:
{prompt}
### Response:
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q2_K.gguf | Q2_K | 0.560 GB | smallest, significant quality loss - not recommended for most purposes |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q3_K_S.gguf | Q3_K_S | 0.642 GB | very small, high quality loss |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q3_K_M.gguf | Q3_K_M | 0.704 GB | very small, high quality loss |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q3_K_L.gguf | Q3_K_L | 0.744 GB | small, substantial quality loss |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q4_0.gguf | Q4_0 | 0.776 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q4_K_S.gguf | Q4_K_S | 0.814 GB | small, greater quality loss |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q4_K_M.gguf | Q4_K_M | 0.873 GB | medium, balanced quality - recommended |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q5_0.gguf | Q5_0 | 0.936 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q5_K_S.gguf | Q5_K_S | 0.953 GB | large, low quality loss - recommended |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q5_K_M.gguf | Q5_K_M | 1.002 GB | large, very low quality loss - recommended |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q6_K.gguf | Q6_K | 1.172 GB | very large, extremely low quality loss |
| asm2asm-deepseek1.3b-xtokenizer-armv8-Q8_0.gguf | Q8_0 | 1.432 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/asm2asm-deepseek1.3b-xtokenizer-armv8-GGUF --include "asm2asm-deepseek1.3b-xtokenizer-armv8-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/asm2asm-deepseek1.3b-xtokenizer-armv8-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'