kuno-royale-v3-7b
Another experimental combination of eren23's ongo-monarch-jaskier merges and Kunoichi-DPO-v2-7B. Untested.
kuno-royale-v3-7b is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- model: SanjiWatsuki/Kunoichi-DPO-v2-7B
layer_range: [0, 32]
- model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v3
layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "core-3/kuno-royale-v3-7b"
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"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 74.88 |
AI2 Reasoning Challenge (25-Shot) | 71.76 |
HellaSwag (10-Shot) | 88.23 |
MMLU (5-Shot) | 65.06 |
TruthfulQA (0-shot) | 71.13 |
Winogrande (5-shot) | 82.32 |
GSM8k (5-shot) | 70.81 |
- Downloads last month
- 68
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 core-3/kuno-royale-v3-7b
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard71.760
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard88.230
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.060
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard71.130
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard70.810