You can deploy this model and start earning money today!

RichardErkhov/
Trelis_-_TinyLlama-chat-SFT-gguf

Name: Trelis_-_TinyLlama-chat-SFT-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLlama-chat-SFT - GGUF

Model creator: https://huggingface.co/Trelis/
Original model: https://huggingface.co/Trelis/TinyLlama-chat-SFT/

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

Original model description:

license: apache-2.0 inference: true datasets:

cerebras/SlimPajama-627B
bigcode/starcoderdata
argilla/dpo-mix-7k language:
en

SFT Fine-tune by Trelis Research

Uses the Llama 2 model template.

Original model card follows below.

TinyLlama-1.1B

https://github.com/jzhang38/TinyLlama

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.

We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.

This Collection

This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.

Eval

Model	Pretrain Tokens	HellaSwag	Obqa	WinoGrande	ARC_c	ARC_e	boolq	piqa	avg
Pythia-1.0B	300B	47.16	31.40	53.43	27.05	48.99	60.83	69.21	48.30
TinyLlama-1.1B-intermediate-step-50K-104b	103B	43.50	29.80	53.28	24.32	44.91	59.66	67.30	46.11
TinyLlama-1.1B-intermediate-step-240k-503b	503B	49.56	31.40	55.80	26.54	48.32	56.91	69.42	48.28
TinyLlama-1.1B-intermediate-step-480k-1007B	1007B	52.54	33.40	55.96	27.82	52.36	59.54	69.91	50.22
TinyLlama-1.1B-intermediate-step-715k-1.5T	1.5T	53.68	35.20	58.33	29.18	51.89	59.08	71.65	51.29
TinyLlama-1.1B-intermediate-step-955k-2T	2T	54.63	33.40	56.83	28.07	54.67	63.21	70.67	51.64
TinyLlama-1.1B-intermediate-step-1195k-2.5T	2.5T	58.96	34.40	58.72	31.91	56.78	63.21	73.07	53.86
TinyLlama-1.1B-intermediate-step-1431k-3T	3T	59.20	36.00	59.12	30.12	55.25	57.83	73.29	52.99

RichardErkhov/Trelis_-_TinyLlama-chat-SFT-gguf