Mistralmash1-7B-s
Mistralmash1-7B-s is a merge of the following models using LazyMergekit:
𧩠Configuration
slices:
- sources:
- model: Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Appended
layer_range: [0, 32]
- model: BAAI/Infinity-Instruct-7M-Gen-mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: Pretergeek/OpenChat-3.5-0106_8.11B_36Layers-Appended
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
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "allknowingroger/Mistralmash1-7B-s"
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. | 20.70 |
IFEval (0-Shot) | 39.61 |
BBH (3-Shot) | 33.45 |
MATH Lvl 5 (4-Shot) | 7.93 |
GPQA (0-shot) | 5.93 |
MuSR (0-shot) | 11.81 |
MMLU-PRO (5-shot) | 25.48 |
- Downloads last month
- 6
Model tree for allknowingroger/Mistralmash1-7B-s
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard39.610
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard33.450
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard7.930
- acc_norm on GPQA (0-shot)Open LLM Leaderboard5.930
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.810
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard25.480