fix(hchat): config cleanup & fixes

feat(models): lowering temp to 0.5 on Nemotron 70B

fix(cookie): set cookie samesite to lax

fix(models): stop token on nemotron

nemotron: add examples (#1528)

feat(models): add `nvidia/Llama-3.1-Nemotron-70B-Instruct-HF` (#1527)

feat(security): add cookie samesite & security settings (#1517)

feat(security): add flag for allowing iframes (#1518)

Revert "Revert "feat(huggingchat): model config update 25-09-2024 (#1494)""

feat: allow custom message to guest users. (#1441)

Revert "feat(huggingchat): model config update 25-09-2024 (#1494)"

feat(huggingchat): model config update 25-09-2024 (#1494)

feat(huggingchat): Model update 24/09/2024 (#1485)

feat(huggingchat): add default instructions to qwen 2.5 (#1483)

feat(huggingchat): add Qwen 2.5 72B (#1481)

feat(tools): remove feature flag for tools and use env variable instead (#1433)

typo

Update prod.yaml (#1460)

chores(hchat): update cohere command R+ to latest version (#1454)

fix(huggingchat): remove app banners (#1426)

build(config): remove 405B from prod config (#1422)

fix(hchat): casing on official tool names

chores(deps): update Transformers to latest version and remove chat templates for all models (#1414)

feat(tools): add FLUX schnell as default image generation tool on HuggingChat

fix(models): correct context window for 405B

fix(featureflags): use correct env vars (#1405)

Community tools (#1250)

fix(featureflags): rewrite feature flag system

Revert "try(auth): fix early access flagging?"

try(auth): fix early access flagging?

fix(config): remove preprompt for huggingchat llama 3.1 (#1358)

feat(auth): Add admin & early access flags based on orgs membership (#1365)

feat(config): improve sampling params for llama 3.1 (#1357)

feat(models): Llama 3.1 support (#1355)

fix(models): Update tokenizer on command R+ (#1345)

fix: prod registry repository (#1340)

remove-internal registry (#1336)

perf: add prod deployment resources (#1333)

Remove Gemma 2 from HuggingChat (#1319)

feat: allow disabling metrics server, consolidate exit handlers (#1201)

Sampling parameters gemma 2

Reduce temp on gemma 2 a bit

Model update 27-06-24 (#1313)

Revert "Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)"

Request less `max_new_tokens` on tools and reduce `truncate` on CMD R+ (#1292)

feat(chart): auto reload when secrets change (#1285)

fix(chart): infisical secret name (#1284)

feat(chart): use infisical (#1276)

Reduce context window on zephyr orpo (#1272)

Revert "Revert "Remove `BODY_SIZE_LIMIT`""