43 lines
1.0 KiB
Markdown
43 lines
1.0 KiB
Markdown
|
---
|
||
|
|
datasets:
|
||
|
|
- GetSoloTech/Code-Reasoning
|
||
|
|
base_model: cublya/Gemma3-Code-Reasoning-4B
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- code-generation
|
||
|
|
- competitive-programming
|
||
|
|
- code-reasoning
|
||
|
|
- programming
|
||
|
|
- algorithms
|
||
|
|
- problem-solving
|
||
|
|
- llama-cpp
|
||
|
|
- gguf-my-repo
|
||
|
|
---
|
||
|
|
|
||
|
|
# lainlives/Gemma3-Code-Reasoning-4B
|
||
|
|
This model contains GGUF format model files for [`cublya/Gemma3-Code-Reasoning-4B`](https://huggingface.co/cublya/Gemma3-Code-Reasoning-4B).
|
||
|
|
|
||
|
|
### Available Quants
|
||
|
|
The following files were generated and uploaded to this repo:
|
||
|
|
`Q4_0`, `Q4_K_S`, `Q4_K_M`, `Q5_0`, `Q5_K_S`, `Q5_K_M`, `Q6_K`, `Q8_0`, `f16`, `bf16`
|
||
|
|
|
||
|
|
### Use with llama.cpp
|
||
|
|
|
||
|
|
CLI:
|
||
|
|
```bash
|
||
|
|
llama-cli --hf-repo lainlives/Gemma3-Code-Reasoning-4B --hf-file Gemma3-Code-Reasoning-4B-Q4_K_M.gguf -p "The meaning to life and the universe is"
|
||
|
|
```
|
||
|
|
|
||
|
|
Server:
|
||
|
|
```bash
|
||
|
|
llama-server --hf-repo lainlives/Gemma3-Code-Reasoning-4B --hf-file Gemma3-Code-Reasoning-4B-Q4_K_M.gguf -c 2048
|
||
|
|
```
|
||
|
|
|
||
|
|
### Or ollama
|
||
|
|
|
||
|
|
CLI:
|
||
|
|
```bash
|
||
|
|
ollama run https://hf.co/lainlives/Gemma3-Code-Reasoning-4B:Q4_K_M
|
||
|
|
```
|