@csabakecskemeti on Hugging Face: "I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge.…"

posted an update 11 days ago

Post

2042

I've made an uncensored version of DeepSeek-R1-Distill-Llama-8B with merge. It's passing the "say f***" censor test.
Tested with lm-evaluation-harness on standard open llm leaderboard tests + hellaswag. Scores are improved in most. Details on the model card.

Model:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B
Quants:
DevQuasar/DevQuasar-R1-Uncensored-Llama-8B-GGUF

Jonathan1998

11 days ago

Will it be competition Chat Gpt or it is temporary and Chat Gpt will still be the best AI?

daleyrob

11 days ago

Can we get a demo space?

csabakecskemeti

10 days ago

Here you can try
https://huggingface.co/spaces/DevQuasar/Mi50

Bust something seems off with my network or with HF everything is very slow.

When llama benched the model I've get 60t/s on the mi50.
Anyway you can try it.

ROCR_VISIBLE_DEVICES=0 build/bin/llama-bench -m ~/Downloads/DevQuasar-R1-Uncensored-Llama-8B.Q8_0.gguf
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon VII, compute capability 9.0, VMM: no

model	size	params	backend	ngl	test	t/s
llama 8B Q8_0	7.95 GiB	8.03 B	ROCm	99	pp512	416.30 ± 0.07
llama 8B Q8_0	7.95 GiB	8.03 B	ROCm	99	tg128	60.13 ± 0.02

Join the conversation