Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,43 @@
|
|
| 1 |
---
|
| 2 |
license: openmdw-1.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openmdw-1.1
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
tags:
|
| 7 |
+
- preview
|
| 8 |
+
- edge
|
| 9 |
+
- code
|
| 10 |
+
- luau
|
| 11 |
---
|
| 12 |
+
# ⚠️ THIS IS A PREVIEW VARIANT OF LUAUDEV! DO NOT USE THIS MODEL FOR PRODUCTION. FOR PRODUCTION WAIT FOR THE OFFICIAL RELEASE
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
When luaudev officially releases, its readme will be more full with information. this is after one stage of sft and pre-training. The base model will be released along side the official instruct model.
|
| 17 |
+
|
| 18 |
+
This is the preview instruct variant.
|
| 19 |
+
|
| 20 |
+
## pre-training info:
|
| 21 |
+
- Luaudev was pre-traiend on 21 billion unique tokens, at 4096 sequence length with packing enabled, with a knowledge cutoff date of march 2026 for code and web and for math may 2025.
|
| 22 |
+
- the model was pre-trained with fp8 matmuls with bf16 weights using the adamwfp8 optimizer and an a effective batch size of 288. All training was done on a single Nvidia RTX 4080 (overclocked)
|
| 23 |
+
|
| 24 |
+
## post-training info:
|
| 25 |
+
- this luaudev variant was post-trained with sft on about 1.5 billion tokens of mixed luau specific code, math, q&a and so on. This model supports 4 reasoning efforts: disabled(no reasoning), low, medium, high. Note the model may loop with high reasoning more than normal. Luaudev also supports tool calling and agentic output and inputs yet for this preview the performance is not ideal.
|
| 26 |
+
|
| 27 |
+
## PLB benchmark results:
|
| 28 |
+
|
| 29 |
+
text:
|
| 30 |
+
Model|Publisher|Elo
|
| 31 |
+
|:---|:---:|:---:|
|
| 32 |
+
GPT OSS 20B **|OpenAI|__**75.4**__ 🏆|
|
| 33 |
+
LuauDev 177M Preview *|**Pinkstack**|56.1|
|
| 34 |
+
Qwen3.5 2B|Qwen|17.3|
|
| 35 |
+
LFM2.5 350M|Liquid AI|11.0|
|
| 36 |
+
Gemma 3 1B|Google|9.5|
|
| 37 |
+
|
| 38 |
+
<small>.* luaudev supports reasoning efforts — set to disabled (reasoning off) for a fair comparison.</small>
|
| 39 |
+
|
| 40 |
+
<small>.** gpt-oss-20b supports reasoning efforts — lowest available is low, so it was set to low.</small>
|
| 41 |
+
|
| 42 |
+
### License:
|
| 43 |
+
Luaudev is released under openmdw 1.1
|