Text Generation
Safetensors
English
llama
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama-3.2
llama-3.2-instruct
llama-3.2-instruct-3b
llama-3
llama-3-instruct
llama-3-instruct-3b
3b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
Eval Results
eval
Browse files
README.md
CHANGED
|
@@ -177,7 +177,7 @@ model-index:
|
|
| 177 |
num_few_shot: 0
|
| 178 |
metrics:
|
| 179 |
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 180 |
-
value:
|
| 181 |
name: strict accuracy
|
| 182 |
source:
|
| 183 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
@@ -192,7 +192,7 @@ model-index:
|
|
| 192 |
num_few_shot: 3
|
| 193 |
metrics:
|
| 194 |
- type: acc_norm
|
| 195 |
-
value: 19.
|
| 196 |
name: normalized accuracy
|
| 197 |
source:
|
| 198 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
@@ -207,7 +207,7 @@ model-index:
|
|
| 207 |
num_few_shot: 4
|
| 208 |
metrics:
|
| 209 |
- type: exact_match
|
| 210 |
-
value: 9.
|
| 211 |
name: exact match
|
| 212 |
source:
|
| 213 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
@@ -237,7 +237,7 @@ model-index:
|
|
| 237 |
num_few_shot: 0
|
| 238 |
metrics:
|
| 239 |
- type: acc_norm
|
| 240 |
-
value:
|
| 241 |
name: acc_norm
|
| 242 |
source:
|
| 243 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
@@ -254,7 +254,7 @@ model-index:
|
|
| 254 |
num_few_shot: 5
|
| 255 |
metrics:
|
| 256 |
- type: acc
|
| 257 |
-
value: 19.
|
| 258 |
name: accuracy
|
| 259 |
source:
|
| 260 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
|
|
| 177 |
num_few_shot: 0
|
| 178 |
metrics:
|
| 179 |
- type: inst_level_strict_acc and prompt_level_strict_acc
|
| 180 |
+
value: 48.9
|
| 181 |
name: strict accuracy
|
| 182 |
source:
|
| 183 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
|
|
| 192 |
num_few_shot: 3
|
| 193 |
metrics:
|
| 194 |
- type: acc_norm
|
| 195 |
+
value: 19.11
|
| 196 |
name: normalized accuracy
|
| 197 |
source:
|
| 198 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
|
|
| 207 |
num_few_shot: 4
|
| 208 |
metrics:
|
| 209 |
- type: exact_match
|
| 210 |
+
value: 9.14
|
| 211 |
name: exact match
|
| 212 |
source:
|
| 213 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
|
|
| 237 |
num_few_shot: 0
|
| 238 |
metrics:
|
| 239 |
- type: acc_norm
|
| 240 |
+
value: 5.49
|
| 241 |
name: acc_norm
|
| 242 |
source:
|
| 243 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|
|
|
|
| 254 |
num_few_shot: 5
|
| 255 |
metrics:
|
| 256 |
- type: acc
|
| 257 |
+
value: 19.1
|
| 258 |
name: accuracy
|
| 259 |
source:
|
| 260 |
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
|