The Thai recipe

TL;DR — the 30-second summarytldr

This chapter is the "crown" of the whole manual — how to make the model answer in Thai well enough to truly replace the cloud you used to pay for; every value you see here passed a criteria-based test (50 real cases, scored by two judge models), not gut feeling

When to usewhen to use

Apply this recipe as soon as the model is installed on the machine (chapter 5) — and come back to it every time you change model or version, because "good parameters" belong to one specific pair (model + dataset) and do not transfer for free across models

How-tohow to

Layer 0 first — the completion safety floor (the most important part, yet the one people overlook): the "strong Thai, weak Thai, alternating" behavior we once hit (thai_ratio swinging 0.72–0.92) is rooted not in the prompt but in truncated or empty answers — the answer ceiling (num_predict) was too small and collided with the model's "inner thoughts"; once the floor is raised correctly, the swing shrinks to a band of just 0.036 and all 300/300 answers come back complete:

# Safety floor (set this before tuning any prompt)
num_ctx: 32768          # below this, long Thai reports get their tails cut off
num_predict: 8192       # long-form writing
num_predict_chat: 2048  # normal chat
num_predict_bot: 1024   # LINE/Telegram bots (30-second UX budget)
think: false            # bot path only — reason below

Source: a 300/300 completions test, Sep 2026 — details in docs/thai.md

The "thinking budget" trap for bots: a reasoning model with think on plus a small num_predict burns the entire answer quota on inner thoughts, then sends back an empty answer — our LINE bot genuinely hit this; the fix is pinning think:false + an answer ceiling sized to the job (already set up in chapter 7)

Layer 1 — the sampling parameters that passed the gate:

# Config A_bom_nothink — the only one of 4 configs tested to pass the 0.78 gate
temperature: 0.7
top_p: 0.8
top_k: 20
repeat_penalty: 1.05    # above this it wrecks code blocks
# Measured: thai_median 0.7821, Han 12 times/28 answers, 17.92 tok/s

Hypotheses the experiments knocked down: presence_penalty 1.5 does "not" make Thai worse (A/B n=23, no difference), and DavidAU's sampling formula did not beat the incumbent (0.7500 vs 0.7821)

Layer 2 — the system prompt recipe "Config G": a 4-part structure (the full 4,101-character version lives in the repo and on Hugging Face bomllm/turbo-thai-config):

1. Identity + personality (a polite Thai assistant, finance/tech domain)
2. Language rule: always answer in Thai (unless the user writes in another language) + absolutely never output Chinese characters (Han ban)
3. Style rule: answer the question first, no padding, no made-up numbers
4. Two example question-answer pairs (few-shot: one general, one report-style)

Config G's measured result: thai_ratio +0.029 over the rival prompt (the 95% CI excludes zero) and stray Chinese characters cut in half (35 → 15 per 100)

If anything gets stuck → chapter 16

Config exampleconfig example

Paste it in for real use — the LiteLLM route (chapter 7) + the file configs/sampling-recipe.yaml in the repo is the "receipt" for every value:

# The ready-made recipe for a 27B model on the Mac (the recipe running in production)
system_prompt : Config G (Thai only + no Chinese characters + 2 few-shot pairs)
temperature   : 0.7      top_p: 0.8     top_k: 20
repeat_penalty: 1.05     presence_penalty: 0.0
num_ctx       : 32768
num_predict   : 8192 long-form / 2048 chat / 1024 bots
think         : false on the bot path, true only on the deep path

Do not remix the values at random — every value here is backed by an experiment, and breakage hurts for real (one typo of repeat_penalty 8.0 = the whole batch of results ruined)

Pro tip — field-tested advicepro tip

FAQfaq

Q: And if the question is in English, which language comes back? — our standard recipe always answers in Thai first (the business owner chose it that way); if you want technical English answered in English, there is a route-level override — but be prepared for the Thai purity number to shift

Q: A new model comes out — do we start over? — the same protocol can simply be re-run (the bench_thai.py script in the repo); a challenger must beat the incumbent with a CI that excludes zero before it gets promoted

For other questions see the FAQ

See alsosee also

• Chapter 5 · Mac Mini — the home of the model that takes this recipe
• Chapter 13 · Bots — where think:false makes the difference
• Hugging Face — the full Thai recipe set

Figuresfigures

Videovideo

Real screen recording for this lesson · click play to hear the summary · not investment advice

▶ Watch the manual video: https://youtu.be/O4hM39cgDCY