Changes / Feeds / meta-llama/Llama-3.1-8B-Instruct
meta-llama/Llama-3.1-8B-Instruct
5 changes to a tracked key since 2024-07-18, newest first. Head as last read: 0e9e39f249a16976918f6564b8830bc894c89659.
GPU memory to fine-tune it, card by card: Llama-3.1-8B-Instruct on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2024-07-30 | x_NXMC-2024-0039 | the chat template text changed but rendered byte-identically on the fixed conversation set (system+user, multi-turn, tool call) (2024-07-30).b2a4d0f33b41 -> 8c22764a7e36 |
| 2024-07-29 | x_NXMC-2024-0038 breaking | the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2024-07-29).4281e96c7cf5 -> b2a4d0f33b41 |
| 2024-07-23 | x_NXMC-2024-0037 breaking | rope_scaling added ({"factor":8,"high_freq_factor":4,"low_freq_factor":1,"ori...); positions are now scaled (2024-07-23).6d52333029e2 -> 91e702621d64 |
| 2024-07-18 | x_NXMC-2024-0036 breaking | EOS changed from [128001,128009] to [128001,128008,128009]; anything fine-tuned or served against the old value stops at a different token (2024-07-18).9b17df7da8b8 -> 6d52333029e2 |
| 2024-07-18 | x_NXMC-2024-0035 breaking | EOS changed from [128001,128009] to [128001,128008,128009]; anything fine-tuned or served against the old value stops at a different token (2024-07-18).bedbcc3b91b6 -> 9b17df7da8b8 |
Pin it, and let a bot move the pin
from_pretrained("meta-llama/Llama-3.1-8B-Instruct", revision="0e9e39f249a16976918f6564b8830bc894c89659")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-Instruct.html)