---
tags:
- merge
- mergekit
- lazymergekit
- FuseAI/FuseChat-7B-VaRM
- occiglot/occiglot-7b-eu5-instruct
- INSAIT-Institute/BgGPT-7B-Instruct-v0.2
base_model:
- FuseAI/FuseChat-7B-VaRM
- occiglot/occiglot-7b-eu5-instruct
- INSAIT-Institute/BgGPT-7B-Instruct-v0.2
---

# FMT-v2

FMT-v2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [FuseAI/FuseChat-7B-VaRM](https://huggingface.co/FuseAI/FuseChat-7B-VaRM)
* [occiglot/occiglot-7b-eu5-instruct](https://huggingface.co/occiglot/occiglot-7b-eu5-instruct)
* [INSAIT-Institute/BgGPT-7B-Instruct-v0.2](https://huggingface.co/INSAIT-Institute/BgGPT-7B-Instruct-v0.2)

## 🧩 Configuration

```yaml
models:
  - model: FuseAI/FuseChat-7B-VaRM
    parameters:
      weight: 1.0
  - model: occiglot/occiglot-7b-eu5-instruct
    parameters:
      weight: 0.75
  - model: INSAIT-Institute/BgGPT-7B-Instruct-v0.2
    parameters:
      weight: 0.55
merge_method: task_arithmetic
base_model: FuseAI/FuseChat-7B-VaRM
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Virt-io/FMT-v2"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```