Files changed (1) hide show
  1. README.md +18 -14
README.md CHANGED
@@ -135,10 +135,27 @@ model-index:
135
 
136
  This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
137
 
138
- # Quantized GGUF
139
 
140
  All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1-GGUF)
141
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
142
  # Prompt Template
143
 
144
  This model uses `ChatML` prompt template:
@@ -218,16 +235,3 @@ outputs = pipeline(
218
  )
219
  print(outputs[0]["generated_text"][len(prompt):])
220
  ```
221
- # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
222
- Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.1)
223
-
224
- | Metric |Value|
225
- |---------------------------------|----:|
226
- |Avg. |78.11|
227
- |AI2 Reasoning Challenge (25-Shot)|71.67|
228
- |HellaSwag (10-Shot) |85.83|
229
- |MMLU (5-Shot) |80.12|
230
- |TruthfulQA (0-shot) |62.11|
231
- |Winogrande (5-shot) |82.87|
232
- |GSM8k (5-shot) |86.05|
233
-
 
135
 
136
  This model is a fine-tune (DPO) of `meta-llama/Meta-Llama-3-70B-Instruct` model.
137
 
138
+ # Quantized GGUF
139
 
140
  All GGUF models are available here: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.1-GGUF)
141
 
142
+ # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
143
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-70B-Instruct-DPO-v0.1)
144
+
145
+ | Metric |Value|
146
+ |---------------------------------|----:|
147
+ |Avg. |78.11|
148
+ |AI2 Reasoning Challenge (25-Shot)|71.67|
149
+ |HellaSwag (10-Shot) |85.83|
150
+ |MMLU (5-Shot) |80.12|
151
+ |TruthfulQA (0-shot) |62.11|
152
+ |Winogrande (5-shot) |82.87|
153
+ |GSM8k (5-shot) |86.05|
154
+
155
+ **Top 10 models on the Leaderboard**
156
+ <img src="./llama-3-70b-top-10.png" alt="Llama-3-70B finet-tuned models" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
157
+
158
+
159
  # Prompt Template
160
 
161
  This model uses `ChatML` prompt template:
 
235
  )
236
  print(outputs[0]["generated_text"][len(prompt):])
237
  ```