adonlee_-_LLaMA_2_13B_SFT_v1.5-gguf

RichardErkhov/adonlee_-_LLaMA_2_13B_SFT_v1.5-gguf

adonlee_-_LLaMA_2_13B_SFT_v1.5-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

114

8% of all-time downloads

All-time downloads

1.4K

Public

Repo size

147 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf171 GB · 100%

At a glance

Access: Public
Created: Aug 4, 2024
Updated: Aug 4, 2024
SHA: 7aa4b0bc

Model card

From the Hugging Face model README

Quantization made by Richard Erkhov.

Github

Discord

Request more models

LLaMA_2_13B_SFT_v1.5 - GGUF

Model creator: https://huggingface.co/adonlee/
Original model: https://huggingface.co/adonlee/LLaMA_2_13B_SFT_v1.5/

Name	Quant method	Size
LLaMA_2_13B_SFT_v1.5.Q2_K.gguf	Q2_K	4.52GB
LLaMA_2_13B_SFT_v1.5.IQ3_XS.gguf	IQ3_XS	4.99GB
LLaMA_2_13B_SFT_v1.5.IQ3_S.gguf	IQ3_S	5.27GB
LLaMA_2_13B_SFT_v1.5.Q3_K_S.gguf	Q3_K_S	5.27GB
LLaMA_2_13B_SFT_v1.5.IQ3_M.gguf	IQ3_M	5.57GB
LLaMA_2_13B_SFT_v1.5.Q3_K.gguf	Q3_K	5.9GB
LLaMA_2_13B_SFT_v1.5.Q3_K_M.gguf	Q3_K_M	5.9GB
LLaMA_2_13B_SFT_v1.5.Q3_K_L.gguf	Q3_K_L	6.45GB
LLaMA_2_13B_SFT_v1.5.IQ4_XS.gguf	IQ4_XS	6.54GB
LLaMA_2_13B_SFT_v1.5.Q4_0.gguf	Q4_0	6.86GB
LLaMA_2_13B_SFT_v1.5.IQ4_NL.gguf	IQ4_NL	6.9GB
LLaMA_2_13B_SFT_v1.5.Q4_K_S.gguf	Q4_K_S	6.91GB
LLaMA_2_13B_SFT_v1.5.Q4_K.gguf	Q4_K	7.33GB
LLaMA_2_13B_SFT_v1.5.Q4_K_M.gguf	Q4_K_M	7.33GB
LLaMA_2_13B_SFT_v1.5.Q4_1.gguf	Q4_1	7.61GB
LLaMA_2_13B_SFT_v1.5.Q5_0.gguf	Q5_0	8.36GB
LLaMA_2_13B_SFT_v1.5.Q5_K_S.gguf	Q5_K_S	8.36GB
LLaMA_2_13B_SFT_v1.5.Q5_K.gguf	Q5_K	8.6GB
LLaMA_2_13B_SFT_v1.5.Q5_K_M.gguf	Q5_K_M	8.6GB
LLaMA_2_13B_SFT_v1.5.Q5_1.gguf	Q5_1	9.1GB
LLaMA_2_13B_SFT_v1.5.Q6_K.gguf	Q6_K	9.95GB
LLaMA_2_13B_SFT_v1.5.Q8_0.gguf	Q8_0	12.88GB

Original model description:

license: apache-2.0

This is a general capability upgrade to Llama-2-13B, using open source data to improve multilingual ability, overall knowledge, extended communication, and technical skill.

This model is primarily recommended as a superior-to-Llama-2 baseline for additional finetuning, not for direct deployment to production as a chat model. The user accepts full responsibility for all outputs.

Created: Aug 4, 2024
Updated: Aug 4, 2024