RichardErkhov/euclaise_-_Echo-3B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Echo-3B - GGUF

• Model creator: https://huggingface.co/euclaise/
• Original model: https://huggingface.co/euclaise/Echo-3B/

Name	Quant method	Size
Echo-3B.Q2_K.gguf	Q2_K	1.01GB
Echo-3B.Q3_K_S.gguf	Q3_K_S	1.17GB
Echo-3B.Q3_K.gguf	Q3_K	1.3GB
Echo-3B.Q3_K_M.gguf	Q3_K_M	1.3GB
Echo-3B.Q3_K_L.gguf	Q3_K_L	1.4GB
Echo-3B.IQ4_XS.gguf	IQ4_XS	1.43GB
Echo-3B.Q4_0.gguf	Q4_0	1.5GB
Echo-3B.IQ4_NL.gguf	IQ4_NL	1.51GB
Echo-3B.Q4_K_S.gguf	Q4_K_S	1.51GB
Echo-3B.Q4_K.gguf	Q4_K	1.59GB
Echo-3B.Q4_K_M.gguf	Q4_K_M	1.59GB
Echo-3B.Q4_1.gguf	Q4_1	1.65GB
Echo-3B.Q5_0.gguf	Q5_0	1.81GB
Echo-3B.Q5_K_S.gguf	Q5_K_S	1.81GB
Echo-3B.Q5_K.gguf	Q5_K	1.86GB
Echo-3B.Q5_K_M.gguf	Q5_K_M	1.86GB
Echo-3B.Q5_1.gguf	Q5_1	1.96GB
Echo-3B.Q6_K.gguf	Q6_K	2.14GB
Echo-3B.Q8_0.gguf	Q8_0	2.77GB

Original model description:

datasets: - pankajmathur/lima_unchained_v1 - CheshireAI/guanaco-unchained - totally-not-an-llm/sharegpt-hyperfiltered-3k - totally-not-an-llm/EverythingLM-data-V3 - LDJnr/Verified-Camel - CollectiveCognition/chats-data-2023-10-16 - Norquinal/claude_multiround_chat_30k - euclaise/WritingPromptsX - euirim/goodwiki - euclaise/MiniCoT - euclaise/SciCoT - euclaise/symtune_mini - euclaise/mathoverflow-accepted - lemonilia/LimaRP

Based on Ferret 3B