sometimesanotion/lamarck-14b-v0.1-prose-model_stock

model

This is a dependency for future merges for Lamarck v0.3. Lamarck's merge process uses these to keep later refinements to the model simple.

Its ancestors were selected for interesting prose, but some of them have no evaluation scores. The GPQA and MUSR scores for this model are a surprise, and suggest that the upstream finetunes are more interesting than expected.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Qwen/Qwen2.5-14B as a base.

Models Merged

The following models were included in the merge:

• EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
• oxyapi/oxy-1-small
• allura-org/TQ2.5-14B-Sugarquill-v1
• sthenno-com/miscii-14b-1028
• arcee-ai/Virtuoso-Small
• underwoods/medius-erebus-magnum-14b

Configuration

The following YAML configuration was used to produce this model:

name:                lamarck-14b-prose-model_stock
merge_method:        model_stock
base_model:          Qwen/Qwen2.5-14B
tokenizer_source:    Qwen/Qwen2.5-14B-Instruct
parameters:
  int8_mask:         false
  normalize:         true
  rescale:           false
models:
  - model:           allura-org/TQ2.5-14B-Sugarquill-v1
  - model:           arcee-ai/Virtuoso-Small
  - model:           EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
  - model:           oxyapi/oxy-1-small
  - model:           sthenno-com/miscii-14b-1028
  - model:           underwoods/medius-erebus-magnum-14b
dtype:               bfloat16
out_dtype:           bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	35.59
IFEval (0-Shot)	42.76
BBH (3-Shot)	49.38
MATH Lvl 5 (4-Shot)	33.61
GPQA (0-shot)	19.13
MuSR (0-shot)	20.27
MMLU-PRO (5-shot)	48.38