---
base_model:
- nectec/Pathumma-llm-text-1.0.0
- ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
- jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8
- Tsunami-th/Tsunami-1.0-7B-Instruct
- ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
- openthaigpt/openthaigpt1.5-7b-instruct
- ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
- scb10x/typhoon2-qwen2.5-7b-instruct
- ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
library_name: transformers
tags:
- mergekit
- merge

---
# Chat Template

ChatML

```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```

```
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}
```

# GGUF

Thank you [mradermacher](https://huggingface.co/mradermacher) for creating the GGUF versions of this model.

  * Static quants - [mradermacher/Qwen2.5-7B-Thai-Instruct-GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Thai-Instruct-GGUF)

# MERGE

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8](https://huggingface.co/jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8) as a base.

### Models Merged

The following models were included in the merge:
* [nectec/Pathumma-llm-text-1.0.0](https://huggingface.co/nectec/Pathumma-llm-text-1.0.0) + [ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3](https://huggingface.co/ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3)
* [Tsunami-th/Tsunami-1.0-7B-Instruct](https://huggingface.co/Tsunami-th/Tsunami-1.0-7B-Instruct) + [ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3](https://huggingface.co/ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3)
* [openthaigpt/openthaigpt1.5-7b-instruct](https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct) + [ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3](https://huggingface.co/ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3)
* [scb10x/typhoon2-qwen2.5-7b-instruct](https://huggingface.co/scb10x/typhoon2-qwen2.5-7b-instruct) + [ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3](https://huggingface.co/ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: openthaigpt/openthaigpt1.5-7b-instruct+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
  - model: Tsunami-th/Tsunami-1.0-7B-Instruct+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
  - model: nectec/Pathumma-llm-text-1.0.0+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
  - model: scb10x/typhoon2-qwen2.5-7b-instruct+ngxson/LoRA-Qwen2.5-7B-Instruct-abliterated-v3
merge_method: model_stock
base_model: jeffmeloy/Qwen2.5-7B-nerd-uncensored-v1.8
parameters:
  filter_wise: false
dtype: float32
```