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): use infisical (#1276)

Reduce context window on zephyr orpo (#1272)

Revert "Revert "Remove `BODY_SIZE_LIMIT`""

Revert "Remove `BODY_SIZE_LIMIT`"

Remove `BODY_SIZE_LIMIT`

Use bytes for body size limit (#1268)

Add body size limit to prod env (#1265)

feat(chart): service account (#1252)

Use the chat template from tokenizer for `01-ai/Yi-1.5-34B-Chat`

Fix issue with system preprompt and tools (#1198)

Set tools back to true (#1194)

Bypass spaces tools rate limit (#1167)

fix(chart): incresase resources (#1175)

Hide tools on prod for now (#1165)

[cohere] reduce max_new_tokens (#1160)

Function calling (#996)

Revert "Uses temperature 0.0 for Phi-3." (#1152)

Uses temperature 0.0 for Phi-3. (#1132)

Update examples for Yi (#1150)

Add 01-ai/Yi-1.5-34B-Chat (#1145)

Make messages before login a aws param (#1130)

Add temperature to Llama 3 70B on HuggingChat (#1119)

fix(chart): remove useless param (#1110)

Ensures more consistent hyperparameters to Phi-3-mini-4k-instruct (#1095)

fix(chart): add ADDRESS_HEADER and XFF_DEPTH for IP rate limiting (#1105)

Kubernetes infra (#1088)