RichardErkhov/jeff31415_-_TinyLlama-1.1B-1T-OpenOrca-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLlama-1.1B-1T-OpenOrca - GGUF

• Model creator: https://huggingface.co/jeff31415/
• Original model: https://huggingface.co/jeff31415/TinyLlama-1.1B-1T-OpenOrca/

Name	Quant method	Size
TinyLlama-1.1B-1T-OpenOrca.Q2_K.gguf	Q2_K	0.4GB
TinyLlama-1.1B-1T-OpenOrca.IQ3_XS.gguf	IQ3_XS	0.44GB
TinyLlama-1.1B-1T-OpenOrca.IQ3_S.gguf	IQ3_S	0.47GB
TinyLlama-1.1B-1T-OpenOrca.Q3_K_S.gguf	Q3_K_S	0.47GB
TinyLlama-1.1B-1T-OpenOrca.IQ3_M.gguf	IQ3_M	0.48GB
TinyLlama-1.1B-1T-OpenOrca.Q3_K.gguf	Q3_K	0.51GB
TinyLlama-1.1B-1T-OpenOrca.Q3_K_M.gguf	Q3_K_M	0.51GB
TinyLlama-1.1B-1T-OpenOrca.Q3_K_L.gguf	Q3_K_L	0.55GB
TinyLlama-1.1B-1T-OpenOrca.IQ4_XS.gguf	IQ4_XS	0.57GB
TinyLlama-1.1B-1T-OpenOrca.Q4_0.gguf	Q4_0	0.59GB
TinyLlama-1.1B-1T-OpenOrca.IQ4_NL.gguf	IQ4_NL	0.6GB
TinyLlama-1.1B-1T-OpenOrca.Q4_K_S.gguf	Q4_K_S	0.6GB
TinyLlama-1.1B-1T-OpenOrca.Q4_K.gguf	Q4_K	0.62GB
TinyLlama-1.1B-1T-OpenOrca.Q4_K_M.gguf	Q4_K_M	0.62GB
TinyLlama-1.1B-1T-OpenOrca.Q4_1.gguf	Q4_1	0.65GB
TinyLlama-1.1B-1T-OpenOrca.Q5_0.gguf	Q5_0	0.71GB
TinyLlama-1.1B-1T-OpenOrca.Q5_K_S.gguf	Q5_K_S	0.71GB
TinyLlama-1.1B-1T-OpenOrca.Q5_K.gguf	Q5_K	0.73GB
TinyLlama-1.1B-1T-OpenOrca.Q5_K_M.gguf	Q5_K_M	0.73GB
TinyLlama-1.1B-1T-OpenOrca.Q5_1.gguf	Q5_1	0.77GB
TinyLlama-1.1B-1T-OpenOrca.Q6_K.gguf	Q6_K	0.84GB
TinyLlama-1.1B-1T-OpenOrca.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: apache-2.0 datasets: - Open-Orca/OpenOrca - bigcode/starcoderdata - cerebras/SlimPajama-627B language: - en

Base model:

PY007/TinyLlama-1.1B-intermediate-step-480k-1T

Dataset:

Fine tuned on OpenOrca GPT4 subset for 1 epoch,Using CHATML format

Model License:

Apache 2.0, following the TinyLlama base model.

Quantisation:

• GPTQ:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GPTQ
• AWQ:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-AWQ
• GGUF:https://huggingface.co/TheBloke/TinyLlama-1.1B-1T-OpenOrca-GGUF

Hardware and training details:

Hardware: 1*RTX A5000, ~16 hours to complete 1 epoch. GPU from autodl.com, cost around $3 for this finetuning. https://wandb.ai/jeff200402/TinyLlama-Orca?workspace= for more details.