47 lines
1.2 KiB
Markdown
47 lines
1.2 KiB
Markdown
---
|
|
license: apache-2.0
|
|
tags:
|
|
- merge
|
|
- mergekit
|
|
- lazymergekit
|
|
---
|
|
|
|
# Chimera-Apex-7B
|
|
|
|
Chimera-Apex-7B is an experimental large language model (LLM) created by merging several high-performance models with the goal of achieving exceptional capabilities.
|
|
|
|
GGUF: https://huggingface.co/mradermacher/Chimera-Apex-7B-GGUF
|
|
|
|
### Tasks:
|
|
|
|
Due to the inclusion of various models, Chimera-Apex-7B is intended to be a general-purpose model capable of handling a wide range of tasks, including:
|
|
|
|
- Conversation
|
|
- Question Answering
|
|
- Code Generation
|
|
- (Possibly) NSFW content generation
|
|
|
|
|
|
### Limitations:
|
|
|
|
- As an experimental model, Chimera-Apex-7B's outputs may not always be perfect or accurate.
|
|
- The merged models might introduce biases present in their training data.
|
|
- It's important to be aware of this limitation when interpreting its outputs.
|
|
|
|
|
|
|
|
## 🧩 Configuration
|
|
|
|
```yaml
|
|
models:
|
|
- model: Azazelle/Half-NSFW_Noromaid-7b
|
|
- model: Endevor/InfinityRP-v1-7B
|
|
- model: FuseAI/FuseChat-7B-VaRM
|
|
merge_method: model_stock
|
|
base_model: cognitivecomputations/dolphin-2.0-mistral-7b
|
|
dtype: bfloat16
|
|
|
|
```
|
|
|
|
Chimera-Apex-7B is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|