sometimesanotion commited on
Commit
9f825cd
1 Parent(s): 8a418e7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md CHANGED
@@ -44,6 +44,29 @@ The prose quality has taken a leap, no doubt also to the way [EVA-UNIT-01/EVA-Qw
44
  The following YAML configuration was used to finalize this model:
45
 
46
  ```yaml
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  name: Lamarck-14B-v0.4-Qwenvergence
48
  merge_method: ties
49
  base_model: sometimesanotion/lamarck-14b-base
 
44
  The following YAML configuration was used to finalize this model:
45
 
46
  ```yaml
47
+ name: Qwenvergence-model_stock
48
+ merge_method: model_stock
49
+ base_model: Qwen/Qwen2.5-14B
50
+ tokenizer_source: base
51
+ parameters:
52
+ int8_mask: true
53
+ normalize: true
54
+ rescale: false
55
+ models:
56
+ - model: allura-org/TQ2.5-14B-Sugarquill-v1
57
+ - model: oxyapi/oxy-1-small
58
+ - model: sthenno-com/miscii-14b-1028
59
+ - model: underwoods/medius-erebus-magnum-14b
60
+ - model: EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
61
+ - model: CultriX/SeQwence-14B-EvolMerge
62
+ - model: arcee-ai/Virtuoso-Small
63
+ - model: VAGOsolutions/SauerkrautLM-v2-14b-DPO
64
+ - model: v000000/Qwen2.5-Lumen-14B
65
+ dtype: bfloat16
66
+ out_dtype: bfloat16
67
+ ---
68
+ # Experimental merge methods involving above models
69
+ ---
70
  name: Lamarck-14B-v0.4-Qwenvergence
71
  merge_method: ties
72
  base_model: sometimesanotion/lamarck-14b-base