The EleutherAI/llemma_7b galaxy

16 models are built on EleutherAI/llemma_7b: 7 quantized, 3 fine-tuned, 3 adapters and 3 merges. Together they were downloaded 2,903 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/llemma_7b-i1-GGUF (quantized), 775 downloads in 30 days
• TheBloke/llemma_7b-GGUF (quantized), 714 downloads in 30 days
• Shams2611/testv5 (finetune), 286 downloads in 30 days
• mradermacher/llemma_7b-GGUF (quantized), 238 downloads in 30 days
• TheBloke/llemma_7b-GPTQ (quantized), 37 downloads in 30 days
• TheBloke/llemma_7b-AWQ (quantized), 24 downloads in 30 days
• JyoP/merged_llemma_codeLlama (merge), 18 downloads in 30 days
• wxgeorge/EleutherAI-llemma_7b (finetune), 16 downloads in 30 days
• JyoP/merged_llemma_codeLlama-ties (merge), 13 downloads in 30 days
• Shams2611/testv4 (finetune), 12 downloads in 30 days
• JyoP/merged_llemma_code_llama_slerp (merge), 11 downloads in 30 days
• AlphaMindLabs/llemma_7b-AWQ.4bit (quantized), 9 downloads in 30 days
• ruruya/komath_beta (adapter), 9 downloads in 30 days
• Srinath-Pulaverthi/llemma_7b-Q4_K_M-GGUF (quantized), 7 downloads in 30 days
• msho/llemma_dpo_sampled (adapter), 6 downloads in 30 days
• msho/llemma_sft (adapter), 6 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.