pandafish-7b / README.md
ichigoberry's picture
Update README.md
8125718 verified
metadata
tags:
  - merge
  - mergekit
  - lazymergekit
license: apache-2.0

pandafish-7b

pandafish-7b is an instruct model based on a Model Stock merge of the following models (via LazyMergekit):

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
  - model: mistralai/Mistral-7B-Instruct-v0.2
  - model: CultriX/NeuralTrix-bf16
  - model: OpenPipe/mistral-ft-optimized-1227
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16

πŸ† Evals

Model Average AGIEval GPT4All TruthfulQA Bigbench
pandafish-7b πŸ“„ 51.99 40 74.23 53.22 40.51
mistralai/Mistral-7B-Instruct-v0.2 πŸ“„ 54.81 38.5 71.64 66.82 42.29

πŸ’» Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "ichigoberry/pandafish-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"])