You can deploy this model and start earning money today!

RichardErkhov/
mychen76_-_mistral-7b-merged-ties-gguf

Name: mychen76_-_mistral-7b-merged-ties-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-merged-ties - GGUF

Model creator: https://huggingface.co/mychen76/
Original model: https://huggingface.co/mychen76/mistral-7b-merged-ties/

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

Original model description:

license: apache-2.0 tags:

merge

mistral-7b-merged-ties

mistral-7b-merged-ties is a merge of the following models:

🧩 Configuration

yaml

models:
    - model: mistralai/Mistral-7B-v0.1  
    - model: OpenPipe/mistral-ft-optimized-1218
      parameters:
        density: 0.5  # density gradient
        weight: 0.3
    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
      parameters:
        density: 0.5
        weight: 0.3  # weight gradient
merge_method: ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mychen76/mistral-7b-merged-ties"

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.	71.37
AI2 Reasoning Challenge (25-Shot)	67.92
HellaSwag (10-Shot)	85.93
MMLU (5-Shot)	64.07
TruthfulQA (0-shot)	61.31
Winogrande (5-shot)	80.03
GSM8k (5-shot)	68.54

RichardErkhov/mychen76_-_mistral-7b-merged-ties-gguf