Commit
•
94d222b
1
Parent(s):
d1268a0
Update README.md (#9)
Browse files- Update README.md (7eab6be0d30ad9c8999737a4de5f76fbe7669659)
README.md
CHANGED
|
@@ -131,11 +131,28 @@ model-index:
|
|
| 131 |
|
| 132 |
This model was developed based on `MaziyarPanahi/Llama-3-8B-Instruct-v0.4` model.
|
| 133 |
|
| 134 |
-
# Quantized GGUF
|
| 135 |
|
| 136 |
All GGUF models are available here: [MaziyarPanahi/Llama-3-8B-Instruct-v0.8-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.8-GGUF)
|
| 137 |
|
| 138 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
# Prompt Template
|
| 140 |
|
| 141 |
This model uses `ChatML` prompt template:
|
|
@@ -211,17 +228,3 @@ outputs = pipeline(
|
|
| 211 |
)
|
| 212 |
print(outputs[0]["generated_text"][len(prompt):])
|
| 213 |
```
|
| 214 |
-
|
| 215 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 216 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-8B-Instruct-v0.8)
|
| 217 |
-
|
| 218 |
-
| Metric |Value|
|
| 219 |
-
|---------------------------------|----:|
|
| 220 |
-
|Avg. |73.20|
|
| 221 |
-
|AI2 Reasoning Challenge (25-Shot)|71.67|
|
| 222 |
-
|HellaSwag (10-Shot) |87.77|
|
| 223 |
-
|MMLU (5-Shot) |68.30|
|
| 224 |
-
|TruthfulQA (0-shot) |63.90|
|
| 225 |
-
|Winogrande (5-shot) |79.08|
|
| 226 |
-
|GSM8k (5-shot) |68.46|
|
| 227 |
-
|
|
|
|
| 131 |
|
| 132 |
This model was developed based on `MaziyarPanahi/Llama-3-8B-Instruct-v0.4` model.
|
| 133 |
|
| 134 |
+
# ⚡ Quantized GGUF
|
| 135 |
|
| 136 |
All GGUF models are available here: [MaziyarPanahi/Llama-3-8B-Instruct-v0.8-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-8B-Instruct-v0.8-GGUF)
|
| 137 |
|
| 138 |
|
| 139 |
+
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 140 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Llama-3-8B-Instruct-v0.8)
|
| 141 |
+
|
| 142 |
+
| Metric |Value|
|
| 143 |
+
|---------------------------------|----:|
|
| 144 |
+
|Avg. |73.20|
|
| 145 |
+
|AI2 Reasoning Challenge (25-Shot)|71.67|
|
| 146 |
+
|HellaSwag (10-Shot) |87.77|
|
| 147 |
+
|MMLU (5-Shot) |68.30|
|
| 148 |
+
|TruthfulQA (0-shot) |63.90|
|
| 149 |
+
|Winogrande (5-shot) |79.08|
|
| 150 |
+
|GSM8k (5-shot) |68.46|
|
| 151 |
+
|
| 152 |
+
`MaziyarPanahi/Llama-3-8B-Instruct-v0.8` is the 5th best-performing 8B model on the Open LLM Leaderboard. (03/06/2024).
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
|
| 156 |
# Prompt Template
|
| 157 |
|
| 158 |
This model uses `ChatML` prompt template:
|
|
|
|
| 228 |
)
|
| 229 |
print(outputs[0]["generated_text"][len(prompt):])
|
| 230 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|