bugfix
Browse files- app.py +85 -83
- latest_results.tsv +18 -18
app.py
CHANGED
|
@@ -154,59 +154,61 @@ with demo:
|
|
| 154 |
|
| 155 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
| 156 |
with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
|
| 157 |
-
with gr.Row():
|
| 158 |
-
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
|
| 206 |
leaderboard_table = gr.components.Dataframe(
|
| 207 |
value=leaderboard_df[
|
| 208 |
[c.name for c in fields(AutoEvalColumn) if c.never_hidden or c.displayed_by_default]
|
| 209 |
-
]
|
|
|
|
|
|
|
| 210 |
headers=[
|
| 211 |
c.name for c in fields(AutoEvalColumn) if c.never_hidden or c.displayed_by_default
|
| 212 |
], ##, if c.never_hidden] + shown_columns,
|
|
@@ -223,40 +225,40 @@ with demo:
|
|
| 223 |
datatype=TYPES,
|
| 224 |
visible=False,
|
| 225 |
)
|
| 226 |
-
search_bar.submit(
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
|
| 230 |
-
|
| 231 |
-
|
| 232 |
-
|
| 233 |
-
|
| 234 |
-
|
| 235 |
-
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
)
|
| 239 |
-
for selector in [
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
| 243 |
-
|
| 244 |
-
|
| 245 |
-
]:
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
| 259 |
-
|
| 260 |
|
| 261 |
with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
|
| 262 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
|
|
|
| 154 |
|
| 155 |
with gr.Tabs(elem_classes="tab-buttons") as tabs:
|
| 156 |
with gr.TabItem("🏅 LLM Benchmark", elem_id="llm-benchmark-tab-table", id=0):
|
| 157 |
+
# with gr.Row():
|
| 158 |
+
# # with gr.Column():
|
| 159 |
+
# # with gr.Row():
|
| 160 |
+
# search_bar = gr.Textbox(
|
| 161 |
+
# placeholder=" 🔍 Search for your model (separate multiple queries with `;`) and press ENTER...",
|
| 162 |
+
# show_label=False,
|
| 163 |
+
# elem_id="search-bar",
|
| 164 |
+
# )
|
| 165 |
+
|
| 166 |
+
# # with gr.Row():
|
| 167 |
+
# # shown_columns = gr.CheckboxGroup(
|
| 168 |
+
# # choices=[c.name for c in fields(AutoEvalColumn) if not c.hidden and not c.never_hidden],
|
| 169 |
+
# # value=[
|
| 170 |
+
# # c.name
|
| 171 |
+
# # for c in fields(AutoEvalColumn)
|
| 172 |
+
# # if c.displayed_by_default and not c.hidden and not c.never_hidden
|
| 173 |
+
# # ],
|
| 174 |
+
# # label="Select columns to show",
|
| 175 |
+
# # elem_id="column-select",
|
| 176 |
+
# # interactive=True,
|
| 177 |
+
# # )
|
| 178 |
+
# # with gr.Row():
|
| 179 |
+
# # deleted_models_visibility = gr.Checkbox(
|
| 180 |
+
# # value=False, label="Show gated/private/deleted models", interactive=True
|
| 181 |
+
# # )
|
| 182 |
+
# # with gr.Column(min_width=320):
|
| 183 |
+
# # with gr.Box(elem_id="box-filter"):
|
| 184 |
+
# filter_columns_type = gr.CheckboxGroup(
|
| 185 |
+
# label="Model types",
|
| 186 |
+
# choices=[t.to_str() for t in ModelType],
|
| 187 |
+
# value=[t.to_str() for t in ModelType],
|
| 188 |
+
# interactive=True,
|
| 189 |
+
# elem_id="filter-columns-type",
|
| 190 |
+
# )
|
| 191 |
+
# # filter_columns_precision = gr.CheckboxGroup(
|
| 192 |
+
# # label="Precision",
|
| 193 |
+
# # choices=[i.value.name for i in Precision],
|
| 194 |
+
# # value=[i.value.name for i in Precision],
|
| 195 |
+
# # interactive=True,
|
| 196 |
+
# # elem_id="filter-columns-precision",
|
| 197 |
+
# # )
|
| 198 |
+
# filter_columns_size = gr.CheckboxGroup(
|
| 199 |
+
# label="Model sizes (in billions of parameters)",
|
| 200 |
+
# choices=list(NUMERIC_INTERVALS.keys()),
|
| 201 |
+
# value=list(NUMERIC_INTERVALS.keys()),
|
| 202 |
+
# interactive=True,
|
| 203 |
+
# elem_id="filter-columns-size",
|
| 204 |
+
# )
|
| 205 |
|
| 206 |
leaderboard_table = gr.components.Dataframe(
|
| 207 |
value=leaderboard_df[
|
| 208 |
[c.name for c in fields(AutoEvalColumn) if c.never_hidden or c.displayed_by_default]
|
| 209 |
+
].applymap(
|
| 210 |
+
lambda x: x if isinstance(x, str) or isinstance(x, float) else round(x["value"], 2)
|
| 211 |
+
), # ,# ] + shown_columns],
|
| 212 |
headers=[
|
| 213 |
c.name for c in fields(AutoEvalColumn) if c.never_hidden or c.displayed_by_default
|
| 214 |
], ##, if c.never_hidden] + shown_columns,
|
|
|
|
| 225 |
datatype=TYPES,
|
| 226 |
visible=False,
|
| 227 |
)
|
| 228 |
+
# search_bar.submit(
|
| 229 |
+
# update_table,
|
| 230 |
+
# [
|
| 231 |
+
# hidden_leaderboard_table_for_search,
|
| 232 |
+
# # None,
|
| 233 |
+
# filter_columns_type,
|
| 234 |
+
# # filter_columns_precision,
|
| 235 |
+
# filter_columns_size,
|
| 236 |
+
# # None,
|
| 237 |
+
# search_bar,
|
| 238 |
+
# ],
|
| 239 |
+
# leaderboard_table,
|
| 240 |
+
# )
|
| 241 |
+
# for selector in [
|
| 242 |
+
# # shown_columns,
|
| 243 |
+
# filter_columns_type,
|
| 244 |
+
# # filter_columns_precision,
|
| 245 |
+
# filter_columns_size,
|
| 246 |
+
# # deleted_models_visibility,
|
| 247 |
+
# ]:
|
| 248 |
+
# selector.change(
|
| 249 |
+
# update_table,
|
| 250 |
+
# [
|
| 251 |
+
# hidden_leaderboard_table_for_search,
|
| 252 |
+
# # None,
|
| 253 |
+
# filter_columns_type,
|
| 254 |
+
# # filter_columns_precision,
|
| 255 |
+
# filter_columns_size,
|
| 256 |
+
# # None,
|
| 257 |
+
# search_bar,
|
| 258 |
+
# ],
|
| 259 |
+
# leaderboard_table,
|
| 260 |
+
# queue=True,
|
| 261 |
+
# )
|
| 262 |
|
| 263 |
with gr.TabItem("📝 About", elem_id="llm-benchmark-tab-table", id=2):
|
| 264 |
gr.Markdown(LLM_BENCHMARKS_TEXT, elem_classes="markdown-text")
|
latest_results.tsv
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
-
eval_name Precision Type T Weight type Architecture Model
|
| 2 |
-
6
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
10 mii-community_zefiro-7b-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
|
|
|
| 1 |
+
eval_name Precision Type T Weight type Architecture Model Avg NLU Avg CFK Avg BFS Avg ⬆️ Hub License #Params (B) Model sha Hub ❤️ Available on the hub Code Data AMI 2020 Agg AMI 2020 Miso ARC-C Belebele GeNTE Neutralizing HaSpeeDe2 HS HaSpeeDe2 Stereo HateCheck HONEST IronITA Irony IronITA Sarcasm ItaCoLA News Sum SENTIPOLC SQuAD it TruthfulQA XCOPA Hellaswag-it
|
| 2 |
+
6 swap-uniba_LLaMAntino-3-ANITA-8B-Inst-DPO-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA</a>" 50.15912285053053 66.8637539701687 69.6423469054011 62.22174124203344 Llama 3 Community License Agreement 8.0 0 True 👁 👁 {'value': 49.61934617107031, 'category': 'NLU'} {'value': 73.58604698054239, 'category': 'NLU'} {'value': 56.484641638225256, 'category': 'CFK'} {'value': 83.55555555555556, 'category': 'NLU'} {'value': 33.8255033557047, 'category': 'BFS'} {'value': 72.24399819126907, 'category': 'BFS'} {'value': 61.627116844508144, 'category': 'BFS'} {'value': 80.51511613552358, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 67.79529918401192, 'category': 'NLU'} {'value': 46.19514665929917, 'category': 'NLU'} {'value': 0.24261234404280246, 'category': 'NLU'} {'value': 33.783978293075634, 'category': 'NLU'} {'value': 46.49499761664646, 'category': 'NLU'} {'value': 71.27317142821833, 'category': 'CFK'} {'value': 68.09423700746308, 'category': 'CFK'} {'value': 73.4, 'category': 'CFK'} {'value': 65.06671977693686, 'category': 'CFK'}
|
| 3 |
+
13 mistralai_Mistral-7B-Instruct-v0.2_bfloat16 bfloat16 fine-tuned 🔶 Delta MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">mistralai/Mistral-7B-Instruct-v0.2</a>" 49.62173851779433 58.69183546703023 69.176267976939 59.163280653921184 Apache 2.0 7.0 0 True 🙈 🙈 {'value': 61.95096430524839, 'category': 'NLU'} {'value': 66.42194008585093, 'category': 'NLU'} {'value': 44.36860068259386, 'category': 'CFK'} {'value': 67.22222222222223, 'category': 'NLU'} {'value': 29.12751677852349, 'category': 'BFS'} {'value': 71.07491292799637, 'category': 'BFS'} {'value': 67.27017961567233, 'category': 'BFS'} {'value': 78.40873056250285, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 59.16469471738617, 'category': 'NLU'} {'value': 55.53851376330874, 'category': 'NLU'} {'value': 0.27708420363666786, 'category': 'NLU'} {'value': 36.377962201593874, 'category': 'NLU'} {'value': 50.02052664310759, 'category': 'NLU'} {'value': 68.04841543730598, 'category': 'CFK'} {'value': 59.24407318497844, 'category': 'CFK'} {'value': 64.2, 'category': 'CFK'} {'value': 57.598088030272855, 'category': 'CFK'}
|
| 4 |
+
8 mii-community_zefiro-7b-dpo-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/mii-community/zefiro-7b-dpo-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">mii-community/zefiro-7b-dpo-ITA</a>" 47.51869156825104 57.89491206679833 68.2055343559792 57.87304599700952 Apache 2.0 7.0 0 True 🙈 👁 {'value': 59.97920997920998, 'category': 'NLU'} {'value': 66.14027143881808, 'category': 'NLU'} {'value': 44.19795221843004, 'category': 'CFK'} {'value': 65.88888888888889, 'category': 'NLU'} {'value': 29.798657718120808, 'category': 'BFS'} {'value': 66.93068606112085, 'category': 'BFS'} {'value': 61.46209894750329, 'category': 'BFS'} {'value': 82.83622905315102, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 58.523449206965395, 'category': 'NLU'} {'value': 54.918191698733956, 'category': 'NLU'} {'value': 0.22337556862808253, 'category': 'NLU'} {'value': 35.66642647158017, 'category': 'NLU'} {'value': 38.80971929318383, 'category': 'NLU'} {'value': 74.34293876621986, 'category': 'CFK'} {'value': 43.34227321311386, 'category': 'CFK'} {'value': 68.4, 'category': 'CFK'} {'value': 59.191396136227844, 'category': 'CFK'}
|
| 5 |
+
5 meta-llama_Meta-Llama-3-8B_bfloat16 bfloat16 pretrained 🟢 Original LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/meta-llama/Meta-Llama-3-8B"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">meta-llama/Meta-Llama-3-8B</a>" 48.29856362856205 57.42199318457142 66.8371135489557 57.51922345402972 Meta Llama 3 Community License 8.0 0 True 🙈 🙈 {'value': 60.02710027100271, 'category': 'NLU'} {'value': 63.14678395603251, 'category': 'NLU'} {'value': 40.529010238907844, 'category': 'CFK'} {'value': 76.0, 'category': 'NLU'} {'value': 29.53020134228188, 'category': 'BFS'} {'value': 65.30297764359561, 'category': 'BFS'} {'value': 59.541073390095356, 'category': 'BFS'} {'value': 79.81131536880565, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 57.31801541230962, 'category': 'NLU'} {'value': 56.750548188367965, 'category': 'NLU'} {'value': 0.2786244415689118, 'category': 'NLU'} {'value': 32.93607461627173, 'category': 'NLU'} {'value': 39.93136214294286, 'category': 'NLU'} {'value': 76.49082768675667, 'category': 'CFK'} {'value': 42.06877766857276, 'category': 'CFK'} {'value': 71.2, 'category': 'CFK'} {'value': 56.8213503286198, 'category': 'CFK'}
|
| 6 |
+
15 mii-community_zefiro-7b-base-ITA_bfloat16 bfloat16 fine-tuned 🔶 Delta MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/mii-community/zefiro-7b-base-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">mii-community/zefiro-7b-base-ITA</a>" 46.70847713397559 57.115645622716485 67.35862672334422 57.06091649334544 Apache 2.0 7.0 0 True 🙈 👁 {'value': 60.14362403797995, 'category': 'NLU'} {'value': 64.54082375784897, 'category': 'NLU'} {'value': 40.955631399317404, 'category': 'CFK'} {'value': 58.55555555555556, 'category': 'NLU'} {'value': 28.456375838926174, 'category': 'BFS'} {'value': 66.12858980217781, 'category': 'BFS'} {'value': 59.74063711314884, 'category': 'BFS'} {'value': 82.46753086246828, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 59.05311714498798, 'category': 'NLU'} {'value': 57.8863223808017, 'category': 'NLU'} {'value': 0.09963712635854956, 'category': 'NLU'} {'value': 34.19887652648641, 'category': 'NLU'} {'value': 39.18986054178559, 'category': 'NLU'} {'value': 75.6692177776856, 'category': 'CFK'} {'value': 46.18926820166605, 'category': 'CFK'} {'value': 66.60000000000001, 'category': 'CFK'} {'value': 56.164110734913365, 'category': 'CFK'}
|
| 7 |
+
10 mii-community_zefiro-7b-sft-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/mii-community/zefiro-7b-sft-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">mii-community/zefiro-7b-sft-ITA</a>" 46.84018585967878 56.40022559897527 67.23695288016117 56.825788112938405 Apache 2.0 7.0 0 True 🙈 👁 {'value': 60.458679319889285, 'category': 'NLU'} {'value': 63.51256529535591, 'category': 'NLU'} {'value': 42.32081911262799, 'category': 'CFK'} {'value': 67.77777777777779, 'category': 'NLU'} {'value': 27.248322147651006, 'category': 'BFS'} {'value': 65.72752014372092, 'category': 'BFS'} {'value': 60.158604473839915, 'category': 'BFS'} {'value': 83.05031763559394, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 52.69566548195397, 'category': 'NLU'} {'value': 51.630329924754, 'category': 'NLU'} {'value': 0.08940878967203518, 'category': 'NLU'} {'value': 34.80608014621687, 'category': 'NLU'} {'value': 43.75098014181036, 'category': 'NLU'} {'value': 74.55382319645513, 'category': 'CFK'} {'value': 42.52003278796414, 'category': 'CFK'} {'value': 67.0, 'category': 'CFK'} {'value': 55.606452897829115, 'category': 'CFK'}
|
| 8 |
+
11 mistralai_Mistral-7B-v0.1_bfloat16 bfloat16 pretrained 🟢 Original MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/mistralai/Mistral-7B-v0.1"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">mistralai/Mistral-7B-v0.1</a>" 46.732352034614806 56.099282379017794 65.68372283507196 56.17178574956819 Apache 2.0 7.0 0 True 🙈 🙈 {'value': 60.52050697114497, 'category': 'NLU'} {'value': 63.66158365032981, 'category': 'NLU'} {'value': 41.21160409556314, 'category': 'CFK'} {'value': 65.66666666666666, 'category': 'NLU'} {'value': 29.53020134228188, 'category': 'BFS'} {'value': 60.38816689466484, 'category': 'BFS'} {'value': 57.907599364752336, 'category': 'BFS'} {'value': 80.59264657366079, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 55.23299236027556, 'category': 'NLU'} {'value': 55.67900219124808, 'category': 'NLU'} {'value': 0.131895692851752, 'category': 'NLU'} {'value': 34.09475870496535, 'category': 'NLU'} {'value': 38.87141003943634, 'category': 'NLU'} {'value': 75.08500650762954, 'category': 'CFK'} {'value': 43.19251190731156, 'category': 'CFK'} {'value': 65.60000000000001, 'category': 'CFK'} {'value': 55.40728938458474, 'category': 'CFK'}
|
| 9 |
+
9 swap-uniba_LLaMAntino-2-chat-13b-hf-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/swap-uniba/LLaMAntino-2-chat-13b-hf-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">swap-uniba/LLaMAntino-2-chat-13b-hf-ITA</a>" 44.43040251782813 56.03239812713 66.71944637887557 55.72741567461123 Llama 2 Community License 13.0 0 True 🙈 👁 {'value': 61.41230947327803, 'category': 'NLU'} {'value': 64.77739009492042, 'category': 'NLU'} {'value': 39.07849829351536, 'category': 'CFK'} {'value': 60.44444444444444, 'category': 'NLU'} {'value': 25.503355704697988, 'category': 'BFS'} {'value': 67.1548291501024, 'category': 'BFS'} {'value': 59.101414060364085, 'category': 'BFS'} {'value': 81.83763297921335, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 57.92048929663609, 'category': 'NLU'} {'value': 52.2777996043644, 'category': 'NLU'} {'value': 0.1015435288181161, 'category': 'NLU'} {'value': 23.81691473597593, 'category': 'NLU'} {'value': 34.69232896418751, 'category': 'NLU'} {'value': 73.10003377486571, 'category': 'CFK'} {'value': 44.43667505800782, 'category': 'CFK'} {'value': 70.39999999999999, 'category': 'CFK'} {'value': 53.146783509261105, 'category': 'CFK'}
|
| 10 |
+
0 meta-llama_Llama-2-13b-hf_bfloat16 bfloat16 pretrained 🟢 Original LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/meta-llama/Llama-2-13b-hf"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">meta-llama/Llama-2-13b-hf</a>" 41.85065195875397 56.39967689118707 61.493331674248495 53.24788684139651 Llama 2 Community License 13.0 0 True 🙈 🙈 {'value': 53.24565637065637, 'category': 'NLU'} {'value': 59.32319654843206, 'category': 'NLU'} {'value': 39.93174061433447, 'category': 'CFK'} {'value': 49.666666666666664, 'category': 'NLU'} {'value': 24.295302013422816, 'category': 'BFS'} {'value': 54.13600451447075, 'category': 'BFS'} {'value': 54.88702987697715, 'category': 'BFS'} {'value': 74.1483219663718, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 50.34584608393744, 'category': 'NLU'} {'value': 49.636673785442774, 'category': 'NLU'} {'value': 0.11758183179468357, 'category': 'NLU'} {'value': 35.09699883531247, 'category': 'NLU'} {'value': 37.37259554778931, 'category': 'NLU'} {'value': 75.22840229480128, 'category': 'CFK'} {'value': 42.91722979615231, 'category': 'CFK'} {'value': 69.39999999999999, 'category': 'CFK'} {'value': 54.52101175064728, 'category': 'CFK'}
|
| 11 |
+
3 swap-uniba_LLaMAntino-2-13b-hf-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/swap-uniba/LLaMAntino-2-13b-hf-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">swap-uniba/LLaMAntino-2-13b-hf-ITA</a>" 42.55180887560955 56.134928395066495 60.86087434667943 53.18253720578516 Llama 2 Community License 13.0 0 True 🙈 👁 {'value': 56.79723502304148, 'category': 'NLU'} {'value': 60.93495016444478, 'category': 'NLU'} {'value': 38.56655290102389, 'category': 'CFK'} {'value': 52.33333333333333, 'category': 'NLU'} {'value': 24.697986577181208, 'category': 'BFS'} {'value': 57.1976786986929, 'category': 'BFS'} {'value': 54.2447910290625, 'category': 'BFS'} {'value': 68.16391542846057, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 56.51605280366516, 'category': 'NLU'} {'value': 51.571111501558086, 'category': 'NLU'} {'value': 0.16387751408972254, 'category': 'NLU'} {'value': 23.495330157527007, 'category': 'NLU'} {'value': 38.60258050721683, 'category': 'NLU'} {'value': 74.20709928774112, 'category': 'CFK'} {'value': 42.12767769734222, 'category': 'CFK'} {'value': 71.8, 'category': 'CFK'} {'value': 53.97331208922525, 'category': 'CFK'}
|
| 12 |
+
2 g8a9_tweety-mistral-7b_bfloat16 bfloat16 fine-tuned 🔶 Delta MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/g8a9/tweety-mistral-7b"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">g8a9/tweety-mistral-7b</a>" 38.661388892098834 54.395439989754266 59.92245878392879 50.99309588859396 Apache 2.0 7.0 0 True 👁 👁 {'value': 56.17170479302832, 'category': 'NLU'} {'value': 56.423255312264054, 'category': 'NLU'} {'value': 37.96928327645051, 'category': 'CFK'} {'value': 49.666666666666664, 'category': 'NLU'} {'value': 27.91946308724832, 'category': 'BFS'} {'value': 53.70259637851317, 'category': 'BFS'} {'value': 53.57434872305199, 'category': 'BFS'} {'value': 64.41588573083048, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 50.21506876304183, 'category': 'NLU'} {'value': 49.42973129711966, 'category': 'NLU'} {'value': 0.11006633622278786, 'category': 'NLU'} {'value': 18.81035591897043, 'category': 'NLU'} {'value': 28.46426204947685, 'category': 'NLU'} {'value': 64.39794432633592, 'category': 'CFK'} {'value': 37.75548120876122, 'category': 'CFK'} {'value': 73.4, 'category': 'CFK'} {'value': 58.45449113722366, 'category': 'CFK'}
|
| 13 |
+
14 meta-llama_Llama-2-7b-hf_bfloat16 bfloat16 pretrained 🟢 Original LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/meta-llama/Llama-2-7b-hf"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">meta-llama/Llama-2-7b-hf</a>" 37.63391313202453 51.72929042818041 58.70465604622213 49.35595320214236 Llama 2 Community License 7.0 0 True 🙈 🙈 {'value': 50.26836062232489, 'category': 'NLU'} {'value': 57.089775606014214, 'category': 'NLU'} {'value': 35.153583617747444, 'category': 'CFK'} {'value': 36.11111111111111, 'category': 'NLU'} {'value': 25.100671140939596, 'category': 'BFS'} {'value': 49.33536331841416, 'category': 'BFS'} {'value': 51.73318260900284, 'category': 'BFS'} {'value': 67.35406316275402, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 47.63910390674802, 'category': 'NLU'} {'value': 48.347086153434084, 'category': 'NLU'} {'value': 0.036528464070504335, 'category': 'NLU'} {'value': 33.756452251726735, 'category': 'NLU'} {'value': 27.82288694076669, 'category': 'NLU'} {'value': 68.6449557225095, 'category': 'CFK'} {'value': 39.16657442183614, 'category': 'CFK'} {'value': 66.0, 'category': 'CFK'} {'value': 49.681338378809, 'category': 'CFK'}
|
| 14 |
+
1 swap-uniba_LLaMAntino-2-7b-hf-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">swap-uniba/LLaMAntino-2-7b-hf-ITA</a>" 34.9414685603479 52.13761513263328 55.65104269523598 47.57670879607239 Llama 2 Community License 7.0 0 True 🙈 👁 {'value': 51.11111111111111, 'category': 'NLU'} {'value': 53.267951636107355, 'category': 'NLU'} {'value': 33.70307167235495, 'category': 'CFK'} {'value': 34.66666666666667, 'category': 'NLU'} {'value': 24.295302013422816, 'category': 'BFS'} {'value': 45.514286626950536, 'category': 'BFS'} {'value': 47.59019966407009, 'category': 'BFS'} {'value': 60.855425171736485, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 47.55193616643805, 'category': 'NLU'} {'value': 46.04838972288254, 'category': 'NLU'} {'value': 0.043130721156949686, 'category': 'NLU'} {'value': 24.582547279426233, 'category': 'NLU'} {'value': 22.260015178994326, 'category': 'NLU'} {'value': 69.30864535653794, 'category': 'CFK'} {'value': 40.48297086291322, 'category': 'CFK'} {'value': 68.0, 'category': 'CFK'} {'value': 49.193387771360285, 'category': 'CFK'}
|
| 15 |
+
7 sapienzanlp_Minerva-3B-base-v1.0_bfloat16 bfloat16 pretrained 🟢 Original MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">sapienzanlp/Minerva-3B-base-v1.0</a>" 32.51780487861425 45.62270743274333 53.03397360999342 43.72482864045033 Apache 2.0 3.0 0 True 🙈 👁 {'value': 49.875480140137604, 'category': 'NLU'} {'value': 52.15633707230505, 'category': 'NLU'} {'value': 30.97269624573379, 'category': 'CFK'} {'value': 24.333333333333336, 'category': 'NLU'} {'value': 23.08724832214765, 'category': 'BFS'} {'value': 48.93622623624203, 'category': 'BFS'} {'value': 45.71528801169143, 'category': 'BFS'} {'value': 47.43110547988597, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 43.13118956315911, 'category': 'NLU'} {'value': 45.77114427860697, 'category': 'NLU'} {'value': -0.015363788820154219, 'category': 'NLU'} {'value': 21.8700732759084, 'category': 'NLU'} {'value': 23.020245154283693, 'category': 'NLU'} {'value': 42.99174436502196, 'category': 'CFK'} {'value': 37.371442699146954, 'category': 'CFK'} {'value': 68.60000000000001, 'category': 'CFK'} {'value': 48.17765385381398, 'category': 'CFK'}
|
| 16 |
+
12 swap-uniba_LLaMAntino-2-chat-7b-hf-ITA_bfloat16 bfloat16 fine-tuned 🔶 Adapter LlamaForCausalLM "<a target=""_blank"" href=""https://huggingface.co/swap-uniba/LLaMAntino-2-chat-7b-hf-ITA"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">swap-uniba/LLaMAntino-2-chat-7b-hf-ITA</a>" 27.755861293433362 46.472723322751754 50.321561903359665 41.51671550651493 Llama 2 Community License 7.0 0 True 🙈 👁 {'value': 47.32809806550469, 'category': 'NLU'} {'value': 43.776841477788466, 'category': 'NLU'} {'value': 29.180887372013654, 'category': 'CFK'} {'value': 28.111111111111107, 'category': 'NLU'} {'value': 23.48993288590604, 'category': 'BFS'} {'value': 41.57668822526659, 'category': 'BFS'} {'value': 41.556830771361305, 'category': 'BFS'} {'value': 44.984357634264406, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 41.716872329343005, 'category': 'NLU'} {'value': 43.53102430893341, 'category': 'NLU'} {'value': -0.02574637563194932, 'category': 'NLU'} {'value': 8.269309204888462, 'category': 'NLU'} {'value': 9.339380225529704, 'category': 'NLU'} {'value': 58.43272201840739, 'category': 'CFK'} {'value': 39.880897484241935, 'category': 'CFK'} {'value': 61.8, 'category': 'CFK'} {'value': 43.06910973909579, 'category': 'CFK'}
|
| 17 |
+
4 sapienzanlp_Minerva-1B-base-v1.0_bfloat16 bfloat16 pretrained 🟢 Original MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/sapienzanlp/Minerva-1B-base-v1.0"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">sapienzanlp/Minerva-1B-base-v1.0</a>" 31.262160888066564 35.95468750733228 53.9028524289684 40.37323360812241 Apache 2.0 1.0 0 True 🙈 👁 {'value': 50.76172656624852, 'category': 'NLU'} {'value': 53.84641914146224, 'category': 'NLU'} {'value': 24.573378839590443, 'category': 'CFK'} {'value': 22.666666666666664, 'category': 'NLU'} {'value': 26.57718120805369, 'category': 'BFS'} {'value': 48.25128927047713, 'category': 'BFS'} {'value': 44.581537708222804, 'category': 'BFS'} {'value': 50.10425395808837, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 46.49541549308013, 'category': 'NLU'} {'value': 45.46046920890855, 'category': 'NLU'} {'value': 0.022249590030925144, 'category': 'NLU'} {'value': 14.27287574762189, 'category': 'NLU'} {'value': 16.571464690513597, 'category': 'NLU'} {'value': 17.48160254077023, 'category': 'CFK'} {'value': 39.747932356260876, 'category': 'CFK'} {'value': 60.0, 'category': 'CFK'} {'value': 37.970523800039835, 'category': 'CFK'}
|
| 18 |
+
16 sapienzanlp_Minerva-350M-base-v1.0_bfloat16 bfloat16 pretrained 🟢 Original MistralForCausalLM "<a target=""_blank"" href=""https://huggingface.co/sapienzanlp/Minerva-350M-base-v1.0"" style=""color: var(--link-text-color); text-decoration: underline;text-decoration-style: dotted;"">sapienzanlp/Minerva-350M-base-v1.0</a>" 27.112649526241633 32.348128725709046 56.325635671949826 38.59547130796684 Apache 2.0 0.35 0 True 🙈 👁 {'value': 45.17543859649123, 'category': 'NLU'} {'value': 35.72145622912868, 'category': 'NLU'} {'value': 24.40273037542662, 'category': 'CFK'} {'value': 22.88888888888889, 'category': 'NLU'} {'value': 52.75167785234899, 'category': 'BFS'} {'value': 41.92832319168979, 'category': 'BFS'} {'value': 40.67042217927179, 'category': 'BFS'} {'value': 46.277755136438564, 'category': 'BFS'} {'value': 100.0, 'category': 'BFS'} {'value': 36.23277134884009, 'category': 'NLU'} {'value': 43.223117993157416, 'category': 'NLU'} {'value': -0.036868413829916326, 'category': 'NLU'} {'value': 10.308018221966565, 'category': 'NLU'} {'value': 23.388373345290127, 'category': 'NLU'} {'value': 4.903980027793706, 'category': 'CFK'} {'value': 43.7486912416563, 'category': 'CFK'} {'value': 56.599999999999994, 'category': 'CFK'} {'value': 32.085241983668595, 'category': 'CFK'}
|