anon7463435254's picture

12 3

anon7463435254

anon7463435254

·

AI & ML interests

None yet

Organizations

None yet

anon7463435254's activity

New activity in turboderp/Cat-Llama-3-70B-instruct 4 months ago

Any plan to release a 8B-instruct version?

#8 opened 4 months ago by

New activity in TheBloke/deepseek-coder-6.7B-instruct-GPTQ 10 months ago

error while loading with exllama and AutoGPTQ

#2 opened 10 months ago by

New activity in Open-Orca/OpenOrcaxOpenChat-Preview2-13B about 1 year ago

Unreliable Benchmarks. Definitely worse than LLaMA2-13b

#5 opened about 1 year ago by

New activity in TheBloke/WizardLM-13B-V1.2-GPTQ about 1 year ago

Receive empty response, regardless of which loader I choose

#2 opened about 1 year ago by

New activity in TheBloke/WizardLM-13B-V1.2-GGML about 1 year ago

It doesn't follow the conversation

#2 opened about 1 year ago by

New activity in TheBloke/Llama-2-13B-chat-GPTQ about 1 year ago

Totally unusable from branch 4bit 32g (screenshots included)

#15 opened about 1 year ago by

New activity in TheBloke/Dolphin-Llama-13B-GPTQ about 1 year ago

Why such a bad output?

#1 opened about 1 year ago by

New activity in TheBloke/wizard-vicuna-13B-GPTQ over 1 year ago

Usual Colab Notebook became extremely slow

#10 opened over 1 year ago by

New activity in junelee/wizard-vicuna-13b over 1 year ago

New version with WizardLM 13B 250K dataset?

#5 opened over 1 year ago by

New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ over 1 year ago

Can't see it better than the censored one. Some advise?

#7 opened over 1 year ago by

New activity in TheBloke/gpt4-x-vicuna-13B-GGML over 1 year ago

Accuracy comparison with wizard-vicuna-13b and stable-vicuna-13b?

#1 opened over 1 year ago by

New activity in CyberTimon/chimera-7b-4bit-128g over 1 year ago

13B 4bit 128g version

#1 opened over 1 year ago by