Downloads · 30 days
23
5% of all-time downloads
llm4decompile-6.7b-uo-ggml-f16
sajattack/llm4decompile-6.7b-uo-ggml-f16
llm4decompile-6.7b-uo-ggml-f16 is a machine learning model from sajattack. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
https://github.com/albertan017/LLM4Decompile converted to gguf for use with https://github.com/ggerganov/llama.cpp
All-time downloads
450
Public
Repo size
13.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf13.5 GB · 100%
At a glance
- Access
- Public
- Created
- Mar 19, 2024
- Updated
- Mar 20, 2024
- SHA
- 9af596db
Model card
From the Hugging Face model README
https://github.com/albertan017/LLM4Decompile converted to gguf for use with https://github.com/ggerganov/llama.cpp
Usage
./main --model ./models/llm4decompile-6.7b-uo-f16.gguf --threads 16 --color -c 2048 -n -1 --repeat-penalty 1.2 -ngl 33 --temp 0.7 -f prompts/llm4decompile.txt
-ngl and --threads values may be lowered to reduce gpu and cpu usage respectively
Prompt Format
# This is the assembly code:
0000000000001139 <main>:
1139: push %rbp
113a: mov %rsp,%rbp
113d: sub $0x10,%rsp
1141: mov %edi,-0x4(%rbp)
1144: mov %rsi,-0x10(%rbp)
1148: lea 0xeb5(%rip),%rax
114f: mov %rax,%rdi
1152: call 1030 <puts@plt>
1157: mov $0x0,%eax
115c: leave
115d: ret
# What is the source code?
- Created
- Mar 19, 2024
- Updated
- Mar 20, 2024