karalala
No user record in our sample, but karalala has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
No user record in our sample, but karalala has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
Results of xlstm are promising but will need larger scale experiments. However they completely messed up benchmarking experiments for various RNN models which in their papers claim comparable and even better performance…
True, but they normally arent this far off. HGRN claims that they outperform transformer for 1B parameter model trained on the pile. HGRN performing 8ppl worse suggests that its useless.
Its xlstm contradicting existing peer reviewed papers lmao. Either xlstm should fix their benchmarks or existing peer reviewed papers should retract. RWKV-v6 > RWKV-v5 > RWKV-v4, not the other way round obviously. HGRN…
Already seeing major flaws in the paper. The benchmarking done in the table 1 is extremely questionable. Their table basically contradicts the results from multiple peer reviewed papers, especially for RNNs which report…