SchubergPhilis/TinyLlama-1.1B-Chat-v0.4-ENG-GGUF

Quantized GGUF model files for TinyLlama-1.1B-Chat-v0.4-ENG from SchubergPhilis

Name	Quant method	Size
tinyllama-1.1b-chat-v0.4-eng.fp16.gguf	fp16	2.20 GB
tinyllama-1.1b-chat-v0.4-eng.q2_k.gguf	q2_k	483.12 MB
tinyllama-1.1b-chat-v0.4-eng.q3_k_m.gguf	q3_k_m	550.83 MB
tinyllama-1.1b-chat-v0.4-eng.q4_k_m.gguf	q4_k_m	668.80 MB
tinyllama-1.1b-chat-v0.4-eng.q5_k_m.gguf	q5_k_m	783.03 MB
tinyllama-1.1b-chat-v0.4-eng.q6_k.gguf	q6_k	904.40 MB
tinyllama-1.1b-chat-v0.4-eng.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

TinyLlama-1.1B-Chat-v0.4-ENG

\ Schuberg Philis
Anoosh Ahmadi

Base Model: TinyLlama-1.1B-intermediate-step-715k-1.5T

Model creator: Zhang Peiyuan
Original model: TinyLlama-1.1B-intermediate-step-715k-1.5T
https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T

Description

This repo contains SafeTensor model files for TinyLlama-1.1B-intermediate-step-715k-1.5T
This model is trained by SchubergPhilis/OpenAssistant-Top1-ENG-V1 English conversations only.