Quantization made by Richard Erkhov.

Zebrafish-7B - GGUF

Model creator: https://huggingface.co/mlabonne/
Original model: https://huggingface.co/mlabonne/Zebrafish-7B/

Name	Quant method	Size
Zebrafish-7B.Q2_K.gguf	Q2_K	2.53GB
Zebrafish-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Zebrafish-7B.IQ3_S.gguf	IQ3_S	2.96GB
Zebrafish-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Zebrafish-7B.IQ3_M.gguf	IQ3_M	3.06GB
Zebrafish-7B.Q3_K.gguf	Q3_K	3.28GB
Zebrafish-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Zebrafish-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Zebrafish-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Zebrafish-7B.Q4_0.gguf	Q4_0	3.83GB
Zebrafish-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Zebrafish-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Zebrafish-7B.Q4_K.gguf	Q4_K	4.07GB
Zebrafish-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Zebrafish-7B.Q4_1.gguf	Q4_1	4.24GB
Zebrafish-7B.Q5_0.gguf	Q5_0	4.65GB
Zebrafish-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Zebrafish-7B.Q5_K.gguf	Q5_K	4.78GB
Zebrafish-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Zebrafish-7B.Q5_1.gguf	Q5_1	5.07GB
Zebrafish-7B.Q6_K.gguf	Q6_K	5.53GB
Zebrafish-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: cc-by-nc-4.0 tags: - merge - mergekit - lazymergekit base_model: - liminerity/M7-7b - rwitz/experiment26-truthy-iter-0

Zebrafish-7B

Zebrafish-7B is my first model using the new merge method called Model Stock.

Zebrafish-7B is a merge of the following models using LazyMergekit:

Special thanks to Charles Goddard for the quick implementation!

🏆 Evaluation

Nous

Model	Average	AGIEval	GPT4All	TruthfulQA	Bigbench
mlabonne/AlphaMonarch-7B 📄	62.74	45.37	77.01	78.39	50.2
mlabonne/Zebrafish-7B 📄	62.41	44.92	77.18	78.25	49.28
mlabonne/Beyonder-4x7B-v3 📄	61.91	45.85	76.67	74.98	50.12
mlabonne/NeuralBeagle14-7B 📄	60.25	46.06	76.77	70.32	47.86
mistralai/Mistral-7B-Instruct-v0.2 📄	54.81	38.5	71.64	66.82	42.29

🧩 Configuration

models:
  - model: mistralai/Mistral-7B-v0.1
  - model: liminerity/M7-7b
  - model: rwitz/experiment26-truthy-iter-0
merge_method: model_stock
base_model: mistralai/Mistral-7B-v0.1
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Zebrafish-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"])