25 lines
823 B
Markdown
25 lines
823 B
Markdown
|
---
|
||
|
|
tags:
|
||
|
|
- gguf
|
||
|
|
- llama.cpp
|
||
|
|
- unsloth
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
# episodic-nothink4-simpo2-gguf : GGUF
|
||
|
|
|
||
|
|
This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
|
||
|
|
|
||
|
|
**Example usage**:
|
||
|
|
- For text only LLMs: `llama-cli -hf kenny2021/episodic-nothink4-simpo2-gguf --jinja`
|
||
|
|
- For multimodal models: `llama-mtmd-cli -hf kenny2021/episodic-nothink4-simpo2-gguf --jinja`
|
||
|
|
|
||
|
|
## Available Model files:
|
||
|
|
- `episodic-nothink4-merged.Q8_0.gguf`
|
||
|
|
- `episodic-nothink4-merged.Q4_K_M.gguf`
|
||
|
|
|
||
|
|
## Note
|
||
|
|
The model's BOS token behavior was adjusted for GGUF compatibility.
|
||
|
|
This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
|
||
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|