Hugging Face's logo

beberik
/
Nyxene-v1-11B

Text Generation
Transformers
Safetensors
mistral
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
beberik commited on
Commit
1af0886
•
1 Parent(s): 2c6f7a6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -57,14 +57,14 @@ parameters:
57
  dtype: bfloat16
58
  ```
59
 
60
- loyal-piano-m7-juanako-11B :
61
  ```
62
  slices:
63
  - sources:
64
  - model: fblgit/juanako-7b-UNA
65
  layer_range: [0, 24]
66
  - sources:
67
- - model: ehartford/dolphin-2.1-mistral-7b
68
  layer_range: [8, 32]
69
  merge_method: passthrough
70
  dtype: bfloat16
@@ -77,7 +77,7 @@ slices:
77
  - model: berkeley-nest/Starling-LM-7B-alpha
78
  layer_range: [0, 24]
79
  - sources:
80
- - model: mlabonne/NeuralHermes-2.5-Mistral-7B
81
  layer_range: [8, 32]
82
  merge_method: passthrough
83
  dtype: bfloat16
@@ -87,7 +87,7 @@ Nyxene-11B :
87
  ```
88
  slices:
89
  - sources:
90
- - model: dolphin-juanako-11B
91
  layer_range: [0, 48]
92
  - model: Starling-NeuralHermes-11B
93
  layer_range: [0, 48]
 
57
  dtype: bfloat16
58
  ```
59
 
60
+ loyal-piano-juanako-11B :
61
  ```
62
  slices:
63
  - sources:
64
  - model: fblgit/juanako-7b-UNA
65
  layer_range: [0, 24]
66
  - sources:
67
+ - model: chargoddard/loyal-piano-m7
68
  layer_range: [8, 32]
69
  merge_method: passthrough
70
  dtype: bfloat16
 
77
  - model: berkeley-nest/Starling-LM-7B-alpha
78
  layer_range: [0, 24]
79
  - sources:
80
+ - model: openaccess-ai-collective/DPOpenHermes-7B
81
  layer_range: [8, 32]
82
  merge_method: passthrough
83
  dtype: bfloat16
 
87
  ```
88
  slices:
89
  - sources:
90
+ - model: loyal-piano-juanako-11B
91
  layer_range: [0, 48]
92
  - model: Starling-NeuralHermes-11B
93
  layer_range: [0, 48]