You can deploy this model and start earning money today!

RichardErkhov/
Kukedlc_-_Neural-4-Maths-7b-gguf

Name: Kukedlc_-_Neural-4-Maths-7b-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Neural-4-Maths-7b - GGUF

Model creator: https://huggingface.co/Kukedlc/
Original model: https://huggingface.co/Kukedlc/Neural-4-Maths-7b/

Name	Quant method	Size
Neural-4-Maths-7b.Q2_K.gguf	Q2_K	2.53GB
Neural-4-Maths-7b.IQ3_XS.gguf	IQ3_XS	2.81GB
Neural-4-Maths-7b.IQ3_S.gguf	IQ3_S	2.96GB
Neural-4-Maths-7b.Q3_K_S.gguf	Q3_K_S	2.95GB
Neural-4-Maths-7b.IQ3_M.gguf	IQ3_M	3.06GB
Neural-4-Maths-7b.Q3_K.gguf	Q3_K	3.28GB
Neural-4-Maths-7b.Q3_K_M.gguf	Q3_K_M	3.28GB
Neural-4-Maths-7b.Q3_K_L.gguf	Q3_K_L	3.56GB
Neural-4-Maths-7b.IQ4_XS.gguf	IQ4_XS	3.67GB
Neural-4-Maths-7b.Q4_0.gguf	Q4_0	3.83GB
Neural-4-Maths-7b.IQ4_NL.gguf	IQ4_NL	3.87GB
Neural-4-Maths-7b.Q4_K_S.gguf	Q4_K_S	3.86GB
Neural-4-Maths-7b.Q4_K.gguf	Q4_K	4.07GB
Neural-4-Maths-7b.Q4_K_M.gguf	Q4_K_M	4.07GB
Neural-4-Maths-7b.Q4_1.gguf	Q4_1	4.24GB
Neural-4-Maths-7b.Q5_0.gguf	Q5_0	4.65GB
Neural-4-Maths-7b.Q5_K_S.gguf	Q5_K_S	4.65GB
Neural-4-Maths-7b.Q5_K.gguf	Q5_K	4.78GB
Neural-4-Maths-7b.Q5_K_M.gguf	Q5_K_M	4.78GB
Neural-4-Maths-7b.Q5_1.gguf	Q5_1	5.07GB
Neural-4-Maths-7b.Q6_K.gguf	Q6_K	5.53GB
Neural-4-Maths-7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

tags:

merge
mergekit
lazymergekit
liminerity/M7-7b
MTSAIR/multi_verse_model
Kukedlc/NeuralSirKrishna-7b
Kukedlc/NeuralMaths-Experiment-7b
Kukedlc/Neural4gsm8k base_model:
liminerity/M7-7b
MTSAIR/multi_verse_model
Kukedlc/NeuralSirKrishna-7b
Kukedlc/NeuralMaths-Experiment-7b
Kukedlc/Neural4gsm8k license: apache-2.0

Neural-4-Maths-7b

Neural-4-Maths-7b is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

models:
  - model: Kukedlc/NeuralSirKrishna-7b
    # No parameters necessary for base model
  - model: liminerity/M7-7b
    parameters:
      density: 0.66
      weight: 0.2
  - model: MTSAIR/multi_verse_model
    parameters:
      density: 0.66
      weight: 0.2
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      density: 0.66
      weight: 0.2
  - model: Kukedlc/NeuralMaths-Experiment-7b
    parameters:
      density: 0.44
      weight: 0.2
  - model: Kukedlc/Neural4gsm8k
    parameters:
      density: 0.44
      weight: 0.2
merge_method: dare_ties
base_model: Kukedlc/NeuralSirKrishna-7b
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Neural-4-Maths-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"])

RichardErkhov/Kukedlc_-_Neural-4-Maths-7b-gguf

Original model description:

Neural-4-Maths-7b

🧩 Configuration

💻 Usage

RichardErkhov/
Kukedlc_-_Neural-4-Maths-7b-gguf