MaziyarPanahi
commited on
Commit
•
30a21b4
1
Parent(s):
95b6eed
Update README.md (#8)
Browse files- Update README.md (6d91f5f5906844f1c330c22787c89546bd7fbfbe)
README.md
CHANGED
@@ -127,9 +127,19 @@ This model is an advanced iteration of the powerful `Qwen/Qwen2.5-72B`, specific
|
|
127 |
|
128 |
Thanks to `mradermacher`: [calme-3.1-instruct-78b-GGUF](https://huggingface.co/mradermacher/calme-3.1-instruct-78b-GGUF)
|
129 |
|
130 |
-
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
131 |
|
132 |
-
Leaderboard 2 coming soon!
|
133 |
|
134 |
# Prompt Template
|
135 |
|
@@ -173,16 +183,3 @@ model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.1-instruct-7
|
|
173 |
|
174 |
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
|
175 |
|
176 |
-
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
177 |
-
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-3.1-instruct-78b)
|
178 |
-
|
179 |
-
| Metric |Value|
|
180 |
-
|-------------------|----:|
|
181 |
-
|Avg. |51.20|
|
182 |
-
|IFEval (0-Shot) |81.36|
|
183 |
-
|BBH (3-Shot) |62.41|
|
184 |
-
|MATH Lvl 5 (4-Shot)|38.75|
|
185 |
-
|GPQA (0-shot) |19.46|
|
186 |
-
|MuSR (0-shot) |36.50|
|
187 |
-
|MMLU-PRO (5-shot) |68.72|
|
188 |
-
|
|
|
127 |
|
128 |
Thanks to `mradermacher`: [calme-3.1-instruct-78b-GGUF](https://huggingface.co/mradermacher/calme-3.1-instruct-78b-GGUF)
|
129 |
|
130 |
+
# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
|
131 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-3.1-instruct-78b)
|
132 |
+
|
133 |
+
| Metric |Value|
|
134 |
+
|-------------------|----:|
|
135 |
+
|Avg. |51.20|
|
136 |
+
|IFEval (0-Shot) |81.36|
|
137 |
+
|BBH (3-Shot) |62.41|
|
138 |
+
|MATH Lvl 5 (4-Shot)|38.75|
|
139 |
+
|GPQA (0-shot) |19.46|
|
140 |
+
|MuSR (0-shot) |36.50|
|
141 |
+
|MMLU-PRO (5-shot) |68.72|
|
142 |
|
|
|
143 |
|
144 |
# Prompt Template
|
145 |
|
|
|
183 |
|
184 |
As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.
|
185 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|