Triangle104 commited on
Commit
c740788
1 Parent(s): 8325ec1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -0
README.md CHANGED
@@ -109,6 +109,26 @@ model-index:
109
  This model was converted to GGUF format from [`flammenai/Flammades-Mistral-Nemo-12B`](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
110
  Refer to the [original model card](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) for more details on the model.
111
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
112
  ## Use with llama.cpp
113
  Install llama.cpp through brew (works on Mac and Linux)
114
 
 
109
  This model was converted to GGUF format from [`flammenai/Flammades-Mistral-Nemo-12B`](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
110
  Refer to the [original model card](https://huggingface.co/flammenai/Flammades-Mistral-Nemo-12B) for more details on the model.
111
 
112
+ ---
113
+ Model details:
114
+ -
115
+ nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B-v2 finetuned on flammenai/Date-DPO-NoAsterisks and jondurbin/truthy-dpo-v0.1.
116
+ Method
117
+
118
+ ORPO tuned with 2x RTX 3090 for 3 epochs.
119
+ Open LLM Leaderboard Evaluation Results
120
+
121
+ Detailed results can be found here
122
+ Metric Value
123
+ Avg. 22.34
124
+ IFEval (0-Shot) 38.42
125
+ BBH (3-Shot) 32.39
126
+ MATH Lvl 5 (4-Shot) 6.19
127
+ GPQA (0-shot) 7.16
128
+ MuSR (0-shot) 20.31
129
+ MMLU-PRO (5-shot) 29.57
130
+
131
+ ---
132
  ## Use with llama.cpp
133
  Install llama.cpp through brew (works on Mac and Linux)
134