Changes / Feeds / meta-llama/Llama-3.1-8B
meta-llama/Llama-3.1-8B
6 changes to a tracked key since 2024-07-14, newest first. Head as last read: d04e592bb4f6aa9cfee91e2e20afa771667e1d4b.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-07-23 | x_NXMC-2024-0128 breaking | rope_scaling added ({"factor":8,"high_freq_factor":4,"low_freq_factor":1,"ori...); positions are now scaled (2024-07-23).9cb1f4b8e2ac -> 13f04ed6f85e |
| 2024-07-23 | x_NXMC-2024-0127 | generation defaults changed (do_sample unset to true, temperature unset to 0.6, top_p unset to 0.9); a call that does not pass these explicitly now generates differently (2024-07-23).b9701d0be774 -> 9cb1f4b8e2ac |
| 2024-07-18 | x_NXMC-2024-0126 | tokenizer model_max_length 1e+30 to 131072; truncation defaults change (2024-07-18).e5c39e551424 -> b9701d0be774 |
| 2024-07-17 | x_NXMC-2024-0125 | the chat template was removed (2024-07-17).f6259a50a13f -> e5c39e551424 |
| 2024-07-16 | x_NXMC-2024-0124 breaking | context window 16384 to 131072 tokens (2024-07-16).01d63cd05cf2 -> f6259a50a13f |
| 2024-07-16 | x_NXMC-2024-0123 breaking | context window 8192 to 16384 tokens (2024-07-16).63565f474219 -> 01d63cd05cf2 |
Pin it, and let a bot move the pin
from_pretrained("meta-llama/Llama-3.1-8B", revision="d04e592bb4f6aa9cfee91e2e20afa771667e1d4b")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/meta-llama/Llama-3.1-8B.html)