---
title: "Chat and generate"
description: "Use the interactive session for conversation and the one-shot command for deterministic scripts."
canonical: "https://www.fermionresearch.com/docs/chat-generate/"
source: "Fermion Research"
---

Docs / Guides

# Chat and generate

Use the interactive session for conversation and the one-shot command for deterministic scripts.

## Interactive chat

```text
fermion chat
fermion chat --model FermionResearch/Neutrino-0.6B-Chat
```

On the native backend, a resident process holds the model and KV cache for the session. Each turn can reuse the existing prefix instead of loading the model and replaying the full conversation. Set `FERMION_SESSION=0` to use one process per turn.

## One-shot generation

```text
fermion generate "Summarize the main argument." --max-new 128
fermion generate --raw "Once upon a time" --max-new 80
```

`--raw` bypasses the chat template. The completion goes to standard output. The final statistics line separately reports wall throughput and steady-state decode throughput.

## Why the defaults differ

| Surface | Temperature | Top p | Repetition penalty | Max new |
| --- | --- | --- | --- | --- |
| chat | 0.01 | 1.0 | 1.05 over 256 tokens | 1024 |
| serve | 0.01 | 1.0 | 1.05 over 256 tokens | 1024 |
| generate | 0.0 | 1.0 | 1.0, disabled | 256 |

Chat and serve use the model’s evaluated conversational settings. Generate stays greedy with repetition penalty disabled so command-line scripts are repeatable. Every setting remains available as a flag.

## Sampling controls

```text
fermion chat --temperature 0.7 --top-p 0.8 --rep-penalty 1.1
fermion generate "List three ideas" --temperature 0 --rep-penalty 1.05
```

Source: [https://www.fermionresearch.com/docs/chat-generate/](https://www.fermionresearch.com/docs/chat-generate/)