You can deploy this model and start earning money today!

RichardErkhov/
refine-ai_-_Power-Llama-3-13b-Instruct-gguf

Name: refine-ai_-_Power-Llama-3-13b-Instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Power-Llama-3-13b-Instruct - GGUF

Model creator: https://huggingface.co/refine-ai/
Original model: https://huggingface.co/refine-ai/Power-Llama-3-13b-Instruct/

Name	Quant method	Size
Power-Llama-3-13b-Instruct.Q2_K.gguf	Q2_K	4.75GB
Power-Llama-3-13b-Instruct.IQ3_XS.gguf	IQ3_XS	5.27GB
Power-Llama-3-13b-Instruct.IQ3_S.gguf	IQ3_S	5.54GB
Power-Llama-3-13b-Instruct.Q3_K_S.gguf	Q3_K_S	5.51GB
Power-Llama-3-13b-Instruct.IQ3_M.gguf	IQ3_M	5.7GB
Power-Llama-3-13b-Instruct.Q3_K.gguf	Q3_K	6.08GB
Power-Llama-3-13b-Instruct.Q3_K_M.gguf	Q3_K_M	6.08GB
Power-Llama-3-13b-Instruct.Q3_K_L.gguf	Q3_K_L	6.58GB
Power-Llama-3-13b-Instruct.IQ4_XS.gguf	IQ4_XS	6.81GB
Power-Llama-3-13b-Instruct.Q4_0.gguf	Q4_0	7.08GB
Power-Llama-3-13b-Instruct.IQ4_NL.gguf	IQ4_NL	7.16GB
Power-Llama-3-13b-Instruct.Q4_K_S.gguf	Q4_K_S	7.13GB
Power-Llama-3-13b-Instruct.Q4_K.gguf	Q4_K	7.51GB
Power-Llama-3-13b-Instruct.Q4_K_M.gguf	Q4_K_M	7.51GB
Power-Llama-3-13b-Instruct.Q4_1.gguf	Q4_1	7.83GB
Power-Llama-3-13b-Instruct.Q5_0.gguf	Q5_0	8.57GB
Power-Llama-3-13b-Instruct.Q5_K_S.gguf	Q5_K_S	8.57GB
Power-Llama-3-13b-Instruct.Q5_K.gguf	Q5_K	8.78GB
Power-Llama-3-13b-Instruct.Q5_K_M.gguf	Q5_K_M	8.78GB
Power-Llama-3-13b-Instruct.Q5_1.gguf	Q5_1	9.31GB
Power-Llama-3-13b-Instruct.Q6_K.gguf	Q6_K	10.14GB
Power-Llama-3-13b-Instruct.Q8_0.gguf	Q8_0	13.13GB

Original model description:

tags:

KingNish
Power Series
llama
llama-3
merge
mergekit
lazymergekit base_model:
meta-llama/Meta-Llama-3-8B-Instruct license: llama3 library_name: transformers pipeline_tag: text-generation

Power Llama 3 13B Instruct

Power Llama 3 13B Instruct is a Very Powerful Model under POWER SERIES. It's Creativity, Problem Solving skills, Maths and Logic is better than Meta Llama 3 70B and Beats all 13b Models.

🧩 Evaluation

Coming Soon

💻 Usage

Same as Llama 3 But Best in Creative writing, Logical Reasoning, Translation, Maths, Coding, etc.

Code

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "refine-ai/Power-Llama-3-13b"
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=4096, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

RichardErkhov/refine-ai_-_Power-Llama-3-13b-Instruct-gguf