You can deploy this model and start earning money today!

RichardErkhov/
louisbrulenaudet_-_Maxine-34B-stock-gguf

Name: louisbrulenaudet_-_Maxine-34B-stock-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Maxine-34B-stock - GGUF

Model creator: https://huggingface.co/louisbrulenaudet/
Original model: https://huggingface.co/louisbrulenaudet/Maxine-34B-stock/

Name	Quant method	Size
Maxine-34B-stock.Q2_K.gguf	Q2_K	11.94GB
Maxine-34B-stock.IQ3_XS.gguf	IQ3_XS	13.26GB
Maxine-34B-stock.IQ3_S.gguf	IQ3_S	13.99GB
Maxine-34B-stock.Q3_K_S.gguf	Q3_K_S	13.93GB
Maxine-34B-stock.IQ3_M.gguf	IQ3_M	14.5GB
Maxine-34B-stock.Q3_K.gguf	Q3_K	15.51GB
Maxine-34B-stock.Q3_K_M.gguf	Q3_K_M	15.51GB
Maxine-34B-stock.Q3_K_L.gguf	Q3_K_L	16.89GB
Maxine-34B-stock.IQ4_XS.gguf	IQ4_XS	17.36GB
Maxine-34B-stock.Q4_0.gguf	Q4_0	18.13GB
Maxine-34B-stock.IQ4_NL.gguf	IQ4_NL	18.3GB
Maxine-34B-stock.Q4_K_S.gguf	Q4_K_S	18.25GB
Maxine-34B-stock.Q4_K.gguf	Q4_K	19.24GB
Maxine-34B-stock.Q4_K_M.gguf	Q4_K_M	19.24GB
Maxine-34B-stock.Q4_1.gguf	Q4_1	20.1GB
Maxine-34B-stock.Q5_0.gguf	Q5_0	22.08GB
Maxine-34B-stock.Q5_K_S.gguf	Q5_K_S	22.08GB
Maxine-34B-stock.Q5_K.gguf	Q5_K	22.65GB
Maxine-34B-stock.Q5_K_M.gguf	Q5_K_M	22.65GB
Maxine-34B-stock.Q5_1.gguf	Q5_1	24.05GB
Maxine-34B-stock.Q6_K.gguf	Q6_K	26.28GB
Maxine-34B-stock.Q8_0.gguf	Q8_0	34.03GB

Original model description:

license: apache-2.0 language:

en library_name: transformers pipeline_tag: text-generation tags:
merge
mergekit
ConvexAI/Luminex-34B-v0.2
fblgit/UNA-34BeagleSimpleMath-32K-v1
chemistry
biology
math base_model:
ConvexAI/Luminex-34B-v0.2
fblgit/UNA-34BeagleSimpleMath-32K-v1 model-index:
name: Maxine-34B-stock results:
- task: type: text-generation metrics:
  - name: Average type: Average value: 77.28
  - name: ARC type: ARC value: 74.06
  - name: GSM8K type: GSM8K value: 72.18
  - name: Winogrande type: Winogrande value: 83.9
  - name: TruthfulQA type: TruthfulQA value: 70.18
  - name: HellaSwag type: HellaSwag value: 86.74 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard

Maxine-34B-stock

Maxine-34B-stock is a merge of the following models:

04-07-2024 - To date, louisbrulenaudet/Maxine-34B-stock is the "Best 🤝 base merges and moerges model of around 30B" on the Open LLM Leaderboard.

Configuration

yaml

models:
    - model: ConvexAI/Luminex-34B-v0.2
    - model: fblgit/UNA-34BeagleSimpleMath-32K-v1
merge_method: model_stock
base_model: abacusai/Smaug-34B-v0.1
dtype: bfloat16

Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "louisbrulenaudet/Maxine-34B-stock"
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"])

Citing & Authors

If you use this code in your research, please use the following BibTeX entry.

BibTeX

@misc{louisbrulenaudet2024,
  author =       {Louis Brulé Naudet},
  title =        {Maxine-34B-stock, an xtraordinary 34B model},
  year =         {2024}
  howpublished = {\url{https://huggingface.co/louisbrulenaudet/Maxine-34B-stock}},
}

Feedback

If you have any feedback, please reach out at louisbrulenaudet@icloud.com.

RichardErkhov/louisbrulenaudet_-_Maxine-34B-stock-gguf