FusionNotus-Gk-MoE-13b-slerp
FusionNotus-Gk-MoE-13b-slerp is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
layer_range: [0, 32]
- model: powermove72/GK-inv-MoE-0.1
layer_range: [0, 32]
merge_method: slerp
base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
parameters:
t:
- filter: self_attn
value: [0, 0.7, 0.3, 0.5, 1]
- filter: mlp
value: [1, 0.3, 0.7, 0.5, 0]
- value: 0.5
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "powermove72/FusionNotus-Gk-MoE-13b-slerp"
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"])
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for powermove72/FusionNotus-Gk-MoE-13b-slerp
Merge model
this model