You can deploy this model and start earning money today!

RichardErkhov/
KaraKaraWitch_-_L3.1-70b-Inori-gguf

Name: KaraKaraWitch_-_L3.1-70b-Inori-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

L3.1-70b-Inori - GGUF

Model creator: https://huggingface.co/KaraKaraWitch/
Original model: https://huggingface.co/KaraKaraWitch/L3.1-70b-Inori/

Name	Quant method	Size
L3.1-70b-Inori.Q2_K.gguf	Q2_K	24.56GB
L3.1-70b-Inori.IQ3_XS.gguf	IQ3_XS	27.29GB
L3.1-70b-Inori.IQ3_S.gguf	IQ3_S	28.79GB
L3.1-70b-Inori.Q3_K_S.gguf	Q3_K_S	28.79GB
L3.1-70b-Inori.IQ3_M.gguf	IQ3_M	29.74GB
L3.1-70b-Inori.Q3_K.gguf	Q3_K	31.91GB
L3.1-70b-Inori.Q3_K_M.gguf	Q3_K_M	31.91GB
L3.1-70b-Inori.Q3_K_L.gguf	Q3_K_L	34.59GB
L3.1-70b-Inori.IQ4_XS.gguf	IQ4_XS	35.64GB
L3.1-70b-Inori.Q4_0.gguf	Q4_0	37.22GB
L3.1-70b-Inori.IQ4_NL.gguf	IQ4_NL	37.58GB
L3.1-70b-Inori.Q4_K_S.gguf	Q4_K_S	37.58GB
L3.1-70b-Inori.Q4_K.gguf	Q4_K	39.6GB
L3.1-70b-Inori.Q4_K_M.gguf	Q4_K_M	39.6GB
L3.1-70b-Inori.Q4_1.gguf	Q4_1	41.27GB
L3.1-70b-Inori.Q5_0.gguf	Q5_0	45.32GB
L3.1-70b-Inori.Q5_K_S.gguf	Q5_K_S	45.32GB
L3.1-70b-Inori.Q5_K.gguf	Q5_K	46.52GB
L3.1-70b-Inori.Q5_K_M.gguf	Q5_K_M	46.52GB
L3.1-70b-Inori.Q5_1.gguf	Q5_1	49.36GB
L3.1-70b-Inori.Q6_K.gguf	Q6_K	53.91GB
L3.1-70b-Inori.Q8_0.gguf	Q8_0	69.83GB

Original model description:

base_model:

abacusai/Dracarys-Llama-3.1-70B-Instruct
Sao10K/L3-70B-Euryale-v2.1
gbueno86/Cathallama-70B
sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
Fizzarolli/L3.1-70b-glitz-v0.2
cyberagent/Llama-3.1-70B-Japanese-Instruct-2407 library_name: transformers tags:
mergekit
merge
abacusai/Dracarys-Llama-3.1-70B-Instruct
Sao10K/L3-70B-Euryale-v2.1
gbueno86/Cathallama-70B
sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
Fizzarolli/L3.1-70b-glitz-v0.2
cyberagent/Llama-3.1-70B-Japanese-Instruct-2407

KaraKaraWitch/L3.1-70b-Inori

Inori is the second 70b for the weekend for me to play around.

Learning from the previous model, I yeeted Hermes into the atmosphere and used Glitz as a base.

Inori takes a different approach by using Model Stock.

Dracarys (I just threw it in, but can be useful for code)
Euryale (You all know it!)
Cathallama (Athene + turboderp_cat)
New Dawn (I heard people like it so I added it in)
Celeste (RP)
Japanese-Instruct (Enhancement of Japanese Language for the weebs out there.)

No Hermes was harmed in the making of this model stock merge.

L3.1-70b-Inori is a merge of the following models using LazyMergekit:

General Thoughts

This model has some weird censorship issues. Soketimes it triggers that it can't generate explicit text while sometimes it doesn't.
For that reason, I don't recommend people to use this model.

Yap / Chat Format

L3 Instruct.

Quants & Hosts

🧩 Configuration

yaml

models:
  - model: Fizzarolli/L3.1-70b-glitz-v0.2
  - model: cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
  - model: Sao10K/L3-70B-Euryale-v2.1
  - model: nothingiisreal/L3.1-70B-Celeste-V0.1-BF16
  - model: sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1
  - model: gbueno86/Cathallama-70B
  - model: abacusai/Dracarys-Llama-3.1-70B-Instruct

merge_method: model_stock
base_model: Fizzarolli/L3.1-70b-glitz-v0.2
parameters:
  normalize: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "KaraKaraWitch/L3.1-70b-Inori"
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"])

RichardErkhov/KaraKaraWitch_-_L3.1-70b-Inori-gguf