You can deploy this model and start earning money today!

RichardErkhov/
Replete-AI_-_Llama-3-13B-gguf

Name: Replete-AI_-_Llama-3-13B-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-13B - GGUF

Model creator: https://huggingface.co/Replete-AI/
Original model: https://huggingface.co/Replete-AI/Llama-3-13B/

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

Original model description:

base_model: [] library_name: transformers license: other license_name: llama-3 license_link: https://llama.meta.com/llama3/license/ thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png"

This is the first version of upscaling llama-3. Version 2 is now out and does not have any of the issues that this version has. Please use version 2 instead. Linked bellow:

https://huggingface.co/Replete-AI/Llama-3-11.5B-v2

Llama-3-13B

Thank you to Meta for the weights for Meta-Llama-3-8B

This is an upscaling of the Llama-3-8B Ai using techniques created for Mistral-Evolved-11b-v0.1. This Ai model has been upscaled from 8b parameters to 13b parameters without any continuous pretraining or fine-tuning.

From testing, the model seems to function perfectly at fp16, but has some issues at 4-bit quantization using bitsandbytes.

The model that was used to create this one is linked below:

https://huggingface.co/meta-llama/Meta-Llama-3-8B

Llama-3-13B

Metric	Value
Avg.	54.61
AI2 Reasoning Challenge (25-Shot)	52.99
HellaSwag (10-Shot)	80.66
MMLU (5-Shot)	62.12
TruthfulQA (0-shot)	39.28
Winogrande (5-shot)	70.72
GSM8k (5-shot)	21.91

Original Meta-Llama-3-8B

Metric	Value
Avg.	62.87
AI2 Reasoning Challenge (25-Shot)	59.47
HellaSwag (10-Shot)	82.09
MMLU (5-Shot)	66.69
TruthfulQA (0-shot)	43.90
Winogrande (5-shot)	77.35
GSM8k (5-shot)	45.34

RichardErkhov/Replete-AI_-_Llama-3-13B-gguf

Original model description:

base_model: [] library_name: transformers license: other license_name: llama-3 license_link: https://llama.meta.com/llama3/license/ thumbnail: "https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png"

RichardErkhov/
Replete-AI_-_Llama-3-13B-gguf