You can deploy this model and start earning money today!

RichardErkhov/
mychen76_-_openmixtral-6x7b-v2-gguf

Name: mychen76_-_openmixtral-6x7b-v2-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

openmixtral-6x7b-v2 - GGUF

Model creator: https://huggingface.co/mychen76/
Original model: https://huggingface.co/mychen76/openmixtral-6x7b-v2/

Name	Quant method	Size
openmixtral-6x7b-v2.Q2_K.gguf	Q2_K	12.04GB
openmixtral-6x7b-v2.IQ3_XS.gguf	IQ3_XS	13.48GB
openmixtral-6x7b-v2.IQ3_S.gguf	IQ3_S	14.25GB
openmixtral-6x7b-v2.Q3_K_S.gguf	Q3_K_S	14.23GB
openmixtral-6x7b-v2.IQ3_M.gguf	IQ3_M	14.49GB
openmixtral-6x7b-v2.Q3_K.gguf	Q3_K	15.79GB
openmixtral-6x7b-v2.Q3_K_M.gguf	Q3_K_M	15.79GB
openmixtral-6x7b-v2.Q3_K_L.gguf	Q3_K_L	17.1GB
openmixtral-6x7b-v2.IQ4_XS.gguf	IQ4_XS	17.79GB
openmixtral-6x7b-v2.Q4_0.gguf	Q4_0	18.6GB
openmixtral-6x7b-v2.IQ4_NL.gguf	IQ4_NL	18.77GB
openmixtral-6x7b-v2.Q4_K_S.gguf	Q4_K_S	18.76GB
openmixtral-6x7b-v2.Q4_K.gguf	Q4_K	19.96GB
openmixtral-6x7b-v2.Q4_K_M.gguf	Q4_K_M	19.96GB
openmixtral-6x7b-v2.Q4_1.gguf	Q4_1	20.65GB
openmixtral-6x7b-v2.Q5_0.gguf	Q5_0	22.7GB
openmixtral-6x7b-v2.Q5_K_S.gguf	Q5_K_S	22.7GB
openmixtral-6x7b-v2.Q5_K.gguf	Q5_K	23.41GB
openmixtral-6x7b-v2.Q5_K_M.gguf	Q5_K_M	23.41GB
openmixtral-6x7b-v2.Q5_1.gguf	Q5_1	24.76GB
openmixtral-6x7b-v2.Q6_K.gguf	Q6_K	27.07GB
openmixtral-6x7b-v2.Q8_0.gguf	Q8_0	35.06GB

Original model description:

license: apache-2.0 tags:

merge

openmixtral-6x7b-v2

Quantized openmixtral-6x7b-merged_v2 is a merge of the following 6x7B models:

🧩 Configuration

yaml

base_model: mlabonne/Marcoro14-7B-slerp
experts:
  - source_model: openchat/openchat-3.5-1210
    positive_prompts:
    - "chat"
    - "assistant"
    - "tell me"
    - "explain"
  - source_model: Weyaxi/Einstein-v4-7B
    positive_prompts:
    - "physics"
    - "biology"
    - "chemistry"
    - "science"    
  - source_model: BioMistral/BioMistral-7B
    positive_prompts:
    - "medical"
    - "pubmed"
    - "healthcare"
    - "health"        
  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
    positive_prompts:
    - "code"
    - "python"
    - "javascript"
    - "programming"
    - "algorithm"
  - source_model: maywell/PiVoT-0.1-Starling-LM-RP
    positive_prompts:
    - "storywriting"
    - "write"
    - "scene"
    - "story"
    - "character"
  - source_model: WizardLM/WizardMath-7B-V1.1
    positive_prompts:
    - "reason"
    - "math"
    - "mathematics"
    - "solve"
    - "count"
tokenizer_source: union

💻 Usage

python

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mychen76/openmixtral-6x7b-v2"

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": "Why the sky is blue"}]
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.	72.33
AI2 Reasoning Challenge (25-Shot)	68.52
HellaSwag (10-Shot)	86.75
MMLU (5-Shot)	65.11
TruthfulQA (0-shot)	65.13
Winogrande (5-shot)	79.87
GSM8k (5-shot)	68.61

RichardErkhov/mychen76_-_openmixtral-6x7b-v2-gguf