johnsnowlabs_-_BioLing-7B-Dare-gguf

RichardErkhov/johnsnowlabs_-_BioLing-7B-Dare-gguf

johnsnowlabs_-_BioLing-7B-Dare-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Downloads · 30 days

7% of all-time downloads

All-time downloads

582

Public

Repo size

82.2 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf95.2 GB · 100%

At a glance

Access: Public
Created: Jun 25, 2024
Updated: Jun 25, 2024
SHA: 3046eab3

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

BioLing-7B-Dare - GGUF

Model creator: https://huggingface.co/johnsnowlabs/
Original model: https://huggingface.co/johnsnowlabs/BioLing-7B-Dare/

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

Original model description:

tags:

merge
mergekit
lazymergekit
BioMistral/BioMistral-7B
Nexusflow/Starling-LM-7B-beta base_model:
BioMistral/BioMistral-7B
Nexusflow/Starling-LM-7B-beta license: apache-2.0

BioLing-7B-Dare

This model is developed by John Snow Labs.

This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at [email protected].

🧩 Configuration

models:
  - model: BioMistral/BioMistral-7B
    parameters:
      density: 0.53
      weight: 0.4
  - model: Nexusflow/Starling-LM-7B-beta
    parameters:
      density: 0.53
      weight: 0.3

merge_method: dare_ties
base_model: BioMistral/BioMistral-7B
parameters:
  int8_mask: true
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johnsnowlabs/BioLing-7B-Dare"
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"])

🏆 Evaluation

Coming Soon!

Created: Jun 25, 2024
Updated: Jun 25, 2024