|
--- |
|
base_model: HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 |
|
license: apache-2.0 |
|
--- |
|
## orpo4ns.gguf is good to go, 2bit also done but not recommended, other quants STILL UPLOADING. |
|
|
|
|
|
# Importance-Matrix quantizations of HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 |
|
# first mixtral8x22b finetune 💫 |
|
|
|
the imatrix.dat file was calcuated over 1000 chunks with wikitext.train.raw( included ) |
|
|
|
Wrote a bit of custom c++ to avoid quantizing certain layers, tested fully compatible with llama.cpp as of 10April2024. |
|
|
|
To put it all asa single file ( this is not needed with llama.cpp as it will autodetect the chunks but can help troubleshooting ollama) |
|
|
|
``` |
|
cat orpo4ns.gguf.part* > orpo4ns.gguf |
|
|
|
``` |
|
careful this can take 5 minutes or up to 10-15 on slow instances, check progress with ls -la |
|
|
|
# Run with llama.cpp |
|
|
|
``` |
|
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp/ && make -j |
|
|
|
./main -m ~/orpo4ns-00001-of-00005.gguf -n 256 -t 64 --temp 0.2 --color -p "How to build a city on mars via aldrin cycler orbits?" |
|
|
|
``` |
|
# Perplexity benchmarks |
|
|
|
Command I used to run these on 48 core CPU only machine, you can add -ngl 16 to offload 16 layers or more to gpu on your own. |
|
|
|
```./perplexity -m ~/orpo4ns.gguf -f wiki.test.raw --chunks 12 -t 48 ``` |
|
|
|
```bash |
|
orpor4ns.gguf 71260MB |
|
[1]2.6970,[2]3.1781,[3]3.7390,[4]3.4159,[5]2.8977,[6]2.7126,[7]2.5597,[8]2.5013,[9]2.5279,[10]2.5175,[11]2.5315,[12]2.5455, |
|
Final estimate: PPL = 2.5455 +/- 0.07697 |
|
|
|
orpo2ns.gguf 44026MB |
|
[1]3.0077,[2]3.5575,[3]4.1028,[4]4.4088,[5]4.2206,[6]4.1056,[7]4.1029,[8]4.1305,[9]4.1791,[10]4.3247,[11]4.4759,[12]4.4659, |
|
Final estimate: PPL = 4.4659 +/- 0.16582 |
|
|
|
orpo2n.gguf 49420MB |
|
[1]3.0082,[2]3.5829,[3]4.1414,[4]4.1671,[5]3.8567,[6]3.7209,[7]3.7150,[8]3.7210,[9]3.8445,[10]3.9332,[11]4.0879,[12]4.0884, |
|
Final estimate: PPL = 4.0884 +/- 0.1499 |
|
``` |
