TriLMs unpacked to FP16 - compatible with any implementation supporting LLaMa architecture in huggingface's transformers format.
AI & ML interests
None defined yet.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
-
SpectraSuite/QuantLM_3.9B_4bit_Unpacked
Text Generation • 4B • Updated • 9 -
SpectraSuite/QuantLM_2.3B_4bit_Unpacked
Text Generation • 2B • Updated • 1 -
SpectraSuite/QuantLM_1.5B_4bit_Unpacked
Text Generation • 2B • Updated • 24 -
SpectraSuite/QuantLM_1.1B_4bit_Unpacked
Text Generation • 1B • Updated • 12
FP16 LLMs with LLaMa architecture, trained on same 300B tokens as TriLMs.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
-
SpectraSuite/QuantLM_3.9B_3bit_Unpacked
Text Generation • 4B • Updated • 23 -
SpectraSuite/QuantLM_2.3B_3bit_Unpacked
Text Generation • 2B • Updated • 2 -
SpectraSuite/QuantLM_1.5B_3bit_Unpacked
Text Generation • 2B • Updated • 16 -
SpectraSuite/QuantLM_1.1B_3bit_Unpacked
Text Generation • 1B • Updated • 5
TriLMs unpacked to FP16 - compatible with any implementation supporting LLaMa architecture in huggingface's transformers format.
FP16 LLMs with LLaMa architecture, trained on same 300B tokens as TriLMs.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
-
SpectraSuite/QuantLM_3.9B_4bit_Unpacked
Text Generation • 4B • Updated • 9 -
SpectraSuite/QuantLM_2.3B_4bit_Unpacked
Text Generation • 2B • Updated • 1 -
SpectraSuite/QuantLM_1.5B_4bit_Unpacked
Text Generation • 2B • Updated • 24 -
SpectraSuite/QuantLM_1.1B_4bit_Unpacked
Text Generation • 1B • Updated • 12
QuantLMs, unpacked to FP16 format - compatible with FP16 GEMMs. After unpacking, QuantLMs have the same architecture as LLaMa.
-
SpectraSuite/QuantLM_3.9B_3bit_Unpacked
Text Generation • 4B • Updated • 23 -
SpectraSuite/QuantLM_2.3B_3bit_Unpacked
Text Generation • 2B • Updated • 2 -
SpectraSuite/QuantLM_1.5B_3bit_Unpacked
Text Generation • 2B • Updated • 16 -
SpectraSuite/QuantLM_1.1B_3bit_Unpacked
Text Generation • 1B • Updated • 5