RichardErkhov/Kukedlc_-_MyModelsMerge-7b-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MyModelsMerge-7b - GGUF

• Model creator: https://huggingface.co/Kukedlc/
• Original model: https://huggingface.co/Kukedlc/MyModelsMerge-7b/

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

Original model description:

tags: - merge - mergekit - lazymergekit - liminerity/M7-7b - Kukedlc/Neural4gsm8k - Kukedlc/Jupiter-k-7B-slerp - Kukedlc/NeuralMaxime-7B-slerp - Kukedlc/NeuralFusion-7b-Dare-Ties - Kukedlc/Neural-Krishna-Multiverse-7b-v3 - Kukedlc/NeuTrixOmniBe-DPO - Kukedlc/NeuralSirKrishna-7b base_model: - liminerity/M7-7b - Kukedlc/Neural4gsm8k - Kukedlc/Jupiter-k-7B-slerp - Kukedlc/NeuralMaxime-7B-slerp - Kukedlc/NeuralFusion-7b-Dare-Ties - Kukedlc/Neural-Krishna-Multiverse-7b-v3 - Kukedlc/NeuTrixOmniBe-DPO - Kukedlc/NeuralSirKrishna-7b license: apache-2.0

MyModelsMerge-7b

MyModelsMerge-7b is a merge of the following models using LazyMergekit:

• liminerity/M7-7b
• Kukedlc/Neural4gsm8k
• Kukedlc/Jupiter-k-7B-slerp
• Kukedlc/NeuralMaxime-7B-slerp
• Kukedlc/NeuralFusion-7b-Dare-Ties
• Kukedlc/Neural-Krishna-Multiverse-7b-v3
• Kukedlc/NeuTrixOmniBe-DPO
• Kukedlc/NeuralSirKrishna-7b

🧩 Configuration

models:
  - model: Kukedlc/NeuralSirKrishna-7b
    # no parameters necessary for base model
  - model: liminerity/M7-7b
    parameters:
      weight: 0.1
      density: 0.88
  - model: Kukedlc/Neural4gsm8k
    parameters:
      weight: 0.1
      density: 0.66
  - model: Kukedlc/Jupiter-k-7B-slerp
    parameters:
      weight: 0.1
      density: 0.66
  - model: Kukedlc/NeuralMaxime-7B-slerp
    parameters:
      weight: 0.1
      density: 0.44
  - model: Kukedlc/NeuralFusion-7b-Dare-Ties
    parameters:
      weight: 0.1
      density: 0.44
  - model: Kukedlc/Neural-Krishna-Multiverse-7b-v3
    parameters:
      weight: 0.2
      density: 0.66
  - model: Kukedlc/NeuTrixOmniBe-DPO
    parameters:
      weight: 0.1
      density: 0.33
  - model: Kukedlc/NeuralSirKrishna-7b
    parameters:
      weight: 0.2
      density: 0.88
merge_method: dare_ties
base_model: Kukedlc/NeuralSirKrishna-7b

parameters:
  int8_mask: true
  normalize: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/MyModelsMerge-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"])