You can deploy this model and start earning money today!

RichardErkhov/
shadowml_-_Mixolar-4x7b-gguf

Name: shadowml_-_Mixolar-4x7b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mixolar-4x7b - GGUF

Model creator: https://huggingface.co/shadowml/
Original model: https://huggingface.co/shadowml/Mixolar-4x7b/

Name	Quant method	Size
Mixolar-4x7b.Q2_K.gguf	Q2_K	12.28GB
Mixolar-4x7b.IQ3_XS.gguf	IQ3_XS	13.74GB
Mixolar-4x7b.IQ3_S.gguf	IQ3_S	14.52GB
Mixolar-4x7b.Q3_K_S.gguf	Q3_K_S	14.5GB
Mixolar-4x7b.IQ3_M.gguf	IQ3_M	14.8GB
Mixolar-4x7b.Q3_K.gguf	Q3_K	16.1GB
Mixolar-4x7b.Q3_K_M.gguf	Q3_K_M	16.1GB
Mixolar-4x7b.Q3_K_L.gguf	Q3_K_L	17.45GB
Mixolar-4x7b.IQ4_XS.gguf	IQ4_XS	18.13GB
Mixolar-4x7b.Q4_0.gguf	Q4_0	18.95GB
Mixolar-4x7b.IQ4_NL.gguf	IQ4_NL	19.13GB
Mixolar-4x7b.Q4_K_S.gguf	Q4_K_S	19.11GB
Mixolar-4x7b.Q4_K.gguf	Q4_K	20.33GB
Mixolar-4x7b.Q4_K_M.gguf	Q4_K_M	20.33GB
Mixolar-4x7b.Q4_1.gguf	Q4_1	21.04GB
Mixolar-4x7b.Q5_0.gguf	Q5_0	23.13GB
Mixolar-4x7b.Q5_K_S.gguf	Q5_K_S	23.13GB
Mixolar-4x7b.Q5_K.gguf	Q5_K	23.84GB
Mixolar-4x7b.Q5_K_M.gguf	Q5_K_M	23.84GB
Mixolar-4x7b.Q5_1.gguf	Q5_1	25.23GB
Mixolar-4x7b.Q6_K.gguf	Q6_K	27.58GB
Mixolar-4x7b.Q8_0.gguf	Q8_0	35.73GB

Original model description:

license: apache-2.0 tags:

moe
merge
mergekit model-index:
name: Mixolar-4x7b results:
- task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
  - type: acc_norm value: 71.08 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
  - type: acc_norm value: 88.44 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
  - type: acc value: 66.29 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
  - type: mc2 value: 71.81 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
  - type: acc value: 83.58 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 63.91 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=shadowml/Mixolar-4x7b name: Open LLM Leaderboard

Mixolar-4x7b

This model is a Mixure of Experts (MoE) made with mergekit (mixtral branch). It uses the following base models:

🧩 Configuration

yaml

base_model: kyujinpy/Sakura-SOLAR-Instruct
gate_mode: hidden
experts:
  - source_model: kyujinpy/Sakura-SOLAR-Instruct
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
    negative_prompts:
    - "mathematics"
    - "reasoning"
  - source_model: jeonsworld/CarbonVillain-en-10.7B-v1
    positive_prompts:
    - "write"
    - "AI"
    - "text"
    - "paragraph"
    negative_prompts:
    - "mathematics"
    - "reasoning"
  - source_model: rishiraj/meow
    positive_prompts:
    - "chat"
    - "say"
    - "what"
    negative_prompts:
    - "mathematics"
    - "reasoning"
  - source_model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
    positive_prompts:
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"
    negative_prompts:
    - "chat"
    - "assistant"
    - "storywriting"

💻 Usage

python

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Mixolar-4x7b"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.18
AI2 Reasoning Challenge (25-Shot)	71.08
HellaSwag (10-Shot)	88.44
MMLU (5-Shot)	66.29
TruthfulQA (0-shot)	71.81
Winogrande (5-shot)	83.58
GSM8k (5-shot)	63.91

RichardErkhov/shadowml_-_Mixolar-4x7b-gguf