Hugging Face's logo

Spectra Suite of Low Bitwdith Models
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

Ayushk44  new activity about 1 month ago
SpectraSuite/TriLM_3.9B_Unpacked:Update README.md
tejasvaidhya  updated a Space 3 months ago
SpectraSuite/README
Ayushk44  authored a paper 5 months ago
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
View all activity

SpectraSuite 's collections 6

TriLMs-Unpacked
TriLMs unpacked to FP16 - compatible with any implementation supporting LLaMa architecture in huggingface's transformers format.
QuantLMs-8Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-4Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-6Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-3Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
TriLMs-Unpacked
TriLMs unpacked to FP16 - compatible with any implementation supporting LLaMa architecture in huggingface's transformers format.
QuantLMs-8Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-6Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-4Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs-3Bit-Unpacked
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.