meta-llama/Llama-2-7b-hf
52 derivatives checked
- TheBloke/Llama-2-7B-GGUF: Quantization
- TheBloke/Llama-2-7B-GPTQ: Quantization
- QuantFactory/Llama2-7B-Hindi-finetuned-GGUF: Full fine-tune
- TheBloke/Llama-2-7B-AWQ: Quantization
- swapnilbp/llama_tweet_ptune: Different architecture
- QuantFactory/RoLlama2-7b-Base-GGUF: Full fine-tune
- ggml-org/Llama-2-7B-GGUF: Same weights, converted
- QuantFactory/emma-500-llama2-7b-GGUF: Full fine-tune
- saraprice/llama2-7B-COT-backdoor-DEPLOYMENT: Full fine-tune
- saraprice/llama2-7B-backdoor-DEPLOYMENT: Full fine-tune
- DevQuasar-8/meta-llama.Llama-2-7b-hf-GGUF: Same weights, converted
- Zihao-Li/mala-500-10b-v2-merged: LoRA-style
- rinna/youri-7b: Full fine-tune
- SergeUSS/Llama-2-7B-GGUF: Quantization
- mahimairaja/tweet-summarization-llama-2-finetuned: Adapter
- QuantFactory/diffullama-GGUF: Full fine-tune
- diffusionfamily/diffullama: Full fine-tune
- elastix-ai/HyperPrune-Llama-2-7B-2to4: LoRA-style
- samaya-ai/promptriever-llama2-7b-v1: Adapter
- elastix-ai/HyperPrune-Llama-2-7B-4to8: LoRA-style
- gasolsun/DynamicRAG-7B: Full fine-tune
- smpanaro/Llama-2-7b-NuGPTQ: LoRA-style (fewer layers)
- cypher-hritam/gujjuGPT-v1: Quantization
- tocsa/llama2-7b-sft-verilog: Full fine-tune
- eci-io/climategpt-7b: Full fine-tune
- PKU-DS-LAB/Fairy2i-W2: Full fine-tune
- MaLA-LM/emma-500-llama2-7b: Full fine-tune
- OpenLLM-Ro/RoLlama2-7b-Base: Full fine-tune
- eci-io/climategpt-7b-fsg: Full fine-tune
- AstroMLab/astrollama-2-7b-chat_aic: Full fine-tune
24 other repos hold byte-for-byte identical weight files.