algorithm's picture

algorithm

algorithm

·

AI & ML interests

AI, Web Crawling

Organizations

New activity in zai-org/GLM-4.6 2 months ago

guys we also need some AIR

#1 opened 3 months ago by

New activity in cerebras/GLM-4.5-Air-REAP-82B-A12B 3 months ago

Preservation of rare knowledge

#3 opened 3 months ago by

New activity in ibm-granite/granite-4.0-h-tiny 3 months ago

My review of granite-4.0-h-tiny

#2 opened 3 months ago by

New activity in huihui-ai/Huihui-GLM-4.5-Air-abliterated-GGUF 3 months ago

FP8 non-GGUF?

#1 opened 5 months ago by

New activity in ServiceNow-AI/Apriel-1.5-15b-Thinker 3 months ago

Unused variable in chat template

#10 opened 3 months ago by

Fix template for llama.cpp

#11 opened 3 months ago by

New activity in XiaomiMiMo/MiMo-7B-RL 8 months ago

Any specific token to turn off thinking mode like no think in qwen 3

#9 opened 8 months ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 about 1 year ago

why is the system prompt missing?

#87 opened about 1 year ago by

New activity in Qwen/QVQ-72B-Preview about 1 year ago

GGUF weights?

#1 opened about 1 year ago by

New activity in mattshumer/Reflection-Llama-3.1-70B over 1 year ago

9.9 vs 9.11 example

#19 opened over 1 year ago by

New activity in zai-org/CogVideoX-5B-Space over 1 year ago

a golden retriever jumps in a swimming pool.

#10 opened over 1 year ago by

New activity in CohereLabs/c4ai-command-r-08-2024 over 1 year ago

The `safety_mode` parameter?

#3 opened over 1 year ago by

New activity in Qwen/Qwen2-0.5B-Instruct-GGUF over 1 year ago

-cml / --chatml has been discontinued in llama.cpp

#1 opened over 1 year ago by

New activity in mistralai/Codestral-22B-v0.1 over 1 year ago

Knowledge cutoff date

#30 opened over 1 year ago by

New activity in Orenguteng/Llama-3-8B-Lexi-Uncensored-GGUF over 1 year ago

Reconverted and requantized with latest GGUF to fix llama3 tokenizer

#5 opened over 1 year ago by

New activity in Orenguteng/Llama-3-8B-Lexi-Uncensored over 1 year ago

Idea for a truly uncensored LLaMa-3-8B

#3 opened over 1 year ago by

New activity in hjhj3168/Llama-3-8b-Orthogonalized-exl2 over 1 year ago

fp16 (and maybe gguf)

#1 opened over 1 year ago by

New activity in Vezora/Mistral-22B-v0.1 over 1 year ago

Base Model or Finetuned Version?

#2 opened almost 2 years ago by

New activity in bartowski/Tess-7B-v2.0-GGUF almost 2 years ago

Chat template

#1 opened almost 2 years ago by

New activity in FuseAI/FuseChat-7B-VaRM almost 2 years ago

How to prompt it correctly?

#6 opened almost 2 years ago by