models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
smol_llama-220M-GQAsmol_llama-101M-GQAsmol_llama-220M-GQA-GGUFsmol_llama-101M-GQA-GGUFsmol_llama-101M-GQA-python-GGUFMixtral-GQA-400m-v2-GGUFsmol_llama-220M-GQA-32k-theta-sft-limarpEYE-Llama_gqaMixtral-GQA-400m-v2cse8803-hw1-openwebtext-gqaopt-125m-gqa-ub-6-best-for-KV-cachefacebook-opt-6.7b-gqa-ub-16-best-for-KV-cachesmol_llama-101M-GQA-pythonsmol_llama-220M-GQA-fineweb_edusmol_llama-220M-GQA-32k-theta-sftsmol_llama-220M-GQA-32k-linearSmall_Language_Model_GQA_48M_Pretrainedsmol_llama-220M-GQA-32k-thetasmol_llama-220M-GQA-bpw2.5Mistral-7B-v0.3-CoDA-GQA-LGQA-1B-InstructMeta-Llama-3.1-405B-Instruct-4.5bpw-gqa-exl2Meta-Llama-3.1-405B-Instruct-4.25bpw-gqa-exl2facebook-opt-6.7b-gqa-ub-16-best-for-q-losssmol_llama-220M-GQA-bpw4Llama-3.2-3B-Instruct-onnx-web-gqasmol_llama-220M-GQA-bpw3.5smol_llama-220M-GQA-bpw5.5Llama-3.2-1B-Instruct-onnx-web-gqaLlama-3.2-3B-Instruct-onnx-web-gqa
