40 lines
3.3 KiB
Markdown
40 lines
3.3 KiB
Markdown
---
|
|
base_model:
|
|
- sometimesanotion/Lamarck-14B-v0.6
|
|
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
|
- sometimesanotion/Lamarck-14B-v0.3
|
|
- sometimesanotion/Qwenvergence-14B-v9
|
|
- sometimesanotion/Qwenvergence-14B-v3-Prose
|
|
- arcee-ai/Virtuoso-Small
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
pipeline_tag: text-generation
|
|
metrics:
|
|
- accuracy
|
|
---
|
|
|
|
---
|
|
|
|
> [!TIP] With no benchmark regressions, mostly gains over the previous release, this version of Lamarck has [broken the 41.0 average](https://shorturl.at/jUqEk) maximum for 14B parameter models. Those providing feedback, thank you!
|
|
|
|
Lamarck 14B v0.7: A generalist merge with emphasis on multi-step reasoning, prose, and multi-language ability. The 14B parameter model class has a lot of strong performers, and Lamarck strives to be well-rounded and solid: 
|
|
|
|
Lamarck is produced by a custom toolchain to automate a process of LoRAs and layer-targeting merges:
|
|
|
|
- **Extracted LoRA adapters from special-purpose merges**
|
|
- **Custom base models and model_stocks, with LoRAs from from [huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2](https://huggingface.co/huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2) to minimize IFEVAL loss often seen in model_stock merges**
|
|
- **Separate branches for aggressive breadcrumbs and conservative DELLA merges**
|
|
- **Highly targeted weight/density gradients for every 2-4 layers, at each stage**
|
|
- **Finalization through SLERP+TIES merges recombining the breadcrumbs and DELLA branches to taste**
|
|
|
|
Lamarck's performance comes from an ancestry that goes back through careful merges to select finetuning work, upcycled and combined. Through intermediate merges, [arcee-ai/Virtuoso-Small](https://huggingface.co/arcee-ai/Virtuoso-Small) [sthenno-com/miscii-14b-1225](https://huggingface.co/sthenno-com/miscii-14b-1225) and [VAGOsolutions/SauerkrautLM-v2-14b-DPO](https://huggingface.co/VAGOsolutions/SauerkrautLM-v2-14b-DPO) are emphasized in early layers for extra BBH; later layers add synergistic influence from [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B), [EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2](https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2), and [CultriX/Qwen2.5-14B-Wernicke](https://huggingface.co/CultriX/Qwen2.5-14B-Wernicke).
|
|
|
|
More subjectively, its prose and translation abilities are boosted by repeated re-emphasis of [Krystalan/DRT-o1-14B](https://huggingface.co/Krystalan/DRT-o1-14B) and [underwoods/medius-erebus-magnum-14b](https://huggingface.co/underwoods/medius-erebus-magnum-14b). Other models found in [sometimesanotion/Qwenvergence-14B-v3-Prose](https://huggingface/sometimesanotion/Qwenvergence-14B-v3-Prose) have their impact on prose quality - and surprising synergy of reasoning.
|
|
|
|
Kudos to @arcee-ai, @deepseek-ai, @Krystalan, @underwoods, @VAGOSolutions, @CultriX, @sthenno-com, and @rombodawg whose models had the most influence. [Vimarckoso v3](https://huggingface.co/sometimesanotion/Qwen2.5-14B-Vimarckoso-v3) has the model card which documents its extended lineage.
|