keXjos/Qwable-v2-mlx-4Bit
Text Generation • 35B • Updated • 19
Datasets:
text stringlengths 455 139k |
|---|
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
USER: Make a new one, it should be a fast paced multiplayer FPS (with optinal bots) with full ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/mo... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
-x--- 161 lane lane 20480 Jun 12 14:08 ..
drwxrwxr-x 3 lane lane 4096 Jun 12 09:49 archives
drwxrwxr-x 86 lane lane 4096 Jun 12 09:52 node_modules
-rw-rw-r-- 1 lane lane 287 Jun 12 09:52 package.json
-rw-rw-r-- ... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
atform — auth, avatars, multiplayer worlds, studio editor, real-time physics — generated in a single shot. Express backend, Three.js 3D rendering, WebSocket multiplayer. 4 pre-built official games, catalog system, friend... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
1 const express = require('express');
2 const path = require('path');
3 const fs = require('fs');
4 const { spawn } = require('child_process');
5
6 const app = express();
7 const PORT = Number(process.env.PORT) || 4000... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
l ray-traced stuff with lots of settings. TL;DR clone CSgo to the best of your ability. Look at the result and refine it
USER: USER: <command-name>/model</command-name>
<command-message>model</command-message... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
d-caveat>
USER: <command-name>/model</command-name>
<command-message>model</command-message>
<command-args></command-args>
USER: <local-command-stdout>Set model to Fable 5 and saved as your defaul... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
lane lane 4096 Jun 12 09:52 node_modules
-rw-rw-r-- 1 lane lane 287 Jun 12 09:52 package.json
-rw-rw-r-- 1 lane lane 37037 Jun 12 09:52 package-lock.json
drwxrwxr-x 4 lane lane 4096 Jun 12 09:49 public
drwxrwx... |
<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
…[earlier truncated]…
-type f | grep -v node_modules | head -40", "description": "Inspect package.json and file tree"}
TOOL RESULT: {
"name": "ai-archives",
"version": "1.0.0",
"description": "AI Archives — only the leaps that matter",... |
End of preview. Expand in Data Studio
Fable-5 SFT Combined (v2) — prepared for Qwable-v2 fine-tuning
9842 rows = union of two Fable-5 SFT corpora, deduplicated by user-side content:
lordx64/agentic-distill-fable-5-sft— 4,659 rows WITH<think>blocks (cleartext reasoning added post-hoc by Glint-Research)lordx64/fable-tool-use-sft— 5,183 rows WITHOUT<think>blocks (pure tool-use from 481 Fable-5 Claude Code sessions)
Verified disjoint via SHA-256 on user-side content (0% overlap). The two corpora cover overlapping sessions but different rendering choices in formatting, so they contribute distinct training rows.
Why combined for v2
Training Qwable-v2 on the union teaches the model both styles:
- With-
<think>rows reinforce reasoning-first behavior (~46% of corpus) - Without-
<think>rows reinforce direct-action behavior (~54% of corpus)
In production, the model should produce reasoning when helpful (long planning) and skip it when the action is obvious. The mixed corpus is the closest thing to that distribution we have.
Row format
Same single-text-column Qwen chat template as v1, but the assistant block may or may not have a <think>...</think> prefix depending on the source row.
License & terms
Inherits AGPL-3.0 from both upstream corpora. Same Anthropic usage-policy considerations apply.
- Downloads last month
- 48
