Nous-Capybara-34B-6.0bpw-h6-exl2
This is trained on the Yi-34B model with 200K context length, for 3 epochs on the Capybara dataset!...
Метка: sft
Nous-Capybara-34B-3.0bpw-h6-exl2
This is trained on the Yi-34B model with 200K context length, for 3 epochs on the Capybara dataset!...
Nous-Capybara-7B-v1.9-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
Dimensity-3B
Dimensity-3B — это тонко настроенная версия фреймворка StableLM, обученная на различных диалоговых данных. Содержит 3 миллиарда параметров. Данная...
Nous-Puffin-70B-GPTQ
Chat & support: TheBloke’s Discord server Want to contribute? TheBloke’s Patreon page TheBloke’s LLM work is generously supported...
ct2fast-falcon-7b-sft-top1-696
Speedup inference while reducing memory by 2x-4x using int8 inference in C++ on CPU or GPU. Checkpoint compatible...
stablelm-7b-sft-v7e3-autogptq-4bit-128g
Версия GPTQ модели Open-Assistant StableLM-7B SFT-7, квантованная с помощью AutoGPTQ Обновит это позже — взгляните на солаб, чтобы...
chat-opt-1.3b-rlhf-critic-deepspeed
We thank the following papers and open-source repositories. We especially thank DeepSpeed for their frameworks as well. [1]...
Qwen3.8-9B-heretic-uncensored-Q4_K_M-GGUF
This model was converted to GGUF format from rohit267/Qwen3.8-9B-heretic-uncensored using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
Qwen3.8-9B-heretic-uncensored-Q5_0-GGUF
This model was converted to GGUF format from rohit267/Qwen3.8-9B-heretic-uncensored using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...