Ministral-8B-slerp
Ministral-8B-slerp is a merge of the following models using LazyMergekit:
𧩠Configuration
slices:
- sources:
- model: prince-canuma/Ministral-8B-Instruct-2410-HF
layer_range: [0, 32]
- model: prince-canuma/Ministral-8B-Instruct-2410-HF
layer_range: [0, 32]
merge_method: slerp
base_model: prince-canuma/Ministral-8B-Instruct-2410-HF
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: float32
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/Ministral-8B-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"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 14.84 |
IFEval (0-Shot) | 19.61 |
BBH (3-Shot) | 25.20 |
MATH Lvl 5 (4-Shot) | 0.00 |
GPQA (0-shot) | 8.28 |
MuSR (0-shot) | 12.40 |
MMLU-PRO (5-shot) | 23.55 |
- Downloads last month
- 24
Model tree for allknowingroger/Ministral-8B-slerp
Base model
mistralai/Ministral-8B-Instruct-2410Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard19.610
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard25.200
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard0.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard8.280
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.400
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard23.550