MarcMistral-7B
MarcMistral-7B is a merge of the following models using LazyMergekit:
As an experiment to find the best base merge to further fine-tuning, expect a lot of experiments named using parts of the component models until a clear winner emerges in the benchmarks
In this case merging the highest MMLU merge with a high ARC merge to see which qualities remain untouched or improv
🧩 Configuration
slices:
- sources:
- model: nfaheem/Marcoroni-7b-DPO-Merge
layer_range: [0, 32]
- model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
layer_range: [0, 32]
merge_method: slerp
base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
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 # fallback for rest of tensors
tokenizer_source: union
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "flemmingmiguel/MarcMistral-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"])