Image-Text-to-Text
Transformers
Safetensors
GGUF
gemma3
turkish
türkiye
english
ai
lamapi
next
next-x1
efficient
text-generation
open-source
4b
huggingface
large-language-model
llm
causal
transformer
artificial-intelligence
machine-learning
ai-research
natural-language-processing
language
multilingual
multimodal
nlp
finetuned
lightweight
creative
summarization
question-answering
chat
generative-ai
optimized
unsloth
trl
sft
chemistry
code
biology
finance
legal
music
art
state-of-the-art
climate
medical
agent
text-generation-inference
Merge
dense
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -149,27 +149,6 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 149 |
|
| 150 |
---
|
| 151 |
|
| 152 |
-
<style>
|
| 153 |
-
table { width:fit-content; border-collapse:separate; border-spacing:0 3px;font-family:system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;color:rgb(255, 255, 255)!important;background:rgb(28, 41, 59);border-radius:16px;padding: 10px; border:none;transition:.2s all ease;}
|
| 154 |
-
thead th { text-align:center; padding:4px 10px; font-size:13px; text-transform:uppercase; color:rgb(255, 255, 255)!important;border:none; }
|
| 155 |
-
tbody tr { transition: transform 0.18s ease, box-shadow 0.18s ease; border:none !important;transition:.2s all ease;border-radius:16px;background:rgba(11, 23, 27, 1);}
|
| 156 |
-
tbody .next:hover {box-shadow:0 6px 15px rgba(0, 76, 148, 0.1);background: rgb(0, 59, 225)}
|
| 157 |
-
tbody tr:hover { box-shadow:0 0px 15px rgba(12, 12, 12, 0.4); background:rgba(17, 34, 53, 1)}
|
| 158 |
-
td { padding:8px 10px;border:0px transparent !important;outline:transparent !important; text-align:center; }
|
| 159 |
-
td:first-child { font-weight:600;text-align:left }
|
| 160 |
-
/* tbody .turkish td { background: rgba(255, 0, 0, 0.2) !important; color:rgb(200,200,200); font-weight:400;border:0px !important; scale:1.0; } */
|
| 161 |
-
/* tbody .next td { background: rgba(0, 89, 255, 0.49)!important; color:rgb(200,200,200); font-weight:600;border:0px !important; scale:1.00;outline:none;border:none !important;} */
|
| 162 |
-
.next{
|
| 163 |
-
background: rgb(0, 89, 255);
|
| 164 |
-
}
|
| 165 |
-
tbody tr td:first-child { border-top-left-radius:12px; border-bottom-left-radius:12px; }
|
| 166 |
-
tbody tr td:last-child { border-top-right-radius:12px; border-bottom-right-radius:12px; }
|
| 167 |
-
strong{
|
| 168 |
-
font-size:16px;font-weight:700;color:rgba(255, 255, 255, 1)!important;
|
| 169 |
-
}
|
| 170 |
-
em{opacity:1;font-size:11px !important;}
|
| 171 |
-
</style>
|
| 172 |
-
|
| 173 |
# Our Next 1B and Next 4B models are leading to all of the tiny models in benchmarks.
|
| 174 |
|
| 175 |
<table>
|
|
@@ -184,14 +163,14 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 184 |
</thead>
|
| 185 |
<tbody>
|
| 186 |
<tr class="next">
|
| 187 |
-
<td data-label="Model">Next 4B preview
|
| 188 |
<td data-label="MMLU (5-shot) %">84.6</td>
|
| 189 |
<td data-label="MMLU-Pro %">66.9</td>
|
| 190 |
<td data-label="GSM8K %">82.7</td>
|
| 191 |
<td data-label="MATH %"><strong>70.5</strong></td>
|
| 192 |
</tr>
|
| 193 |
<tr class="next">
|
| 194 |
-
<td data-label="Model">Next 1B
|
| 195 |
<td data-label="MMLU (5-shot) %"><strong>87.3</strong></td>
|
| 196 |
<td data-label="MMLU-Pro %"><strong>69.2</strong></td>
|
| 197 |
<td data-label="GSM8K %"><strong>90.5</strong></td>
|
|
@@ -229,32 +208,32 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 229 |
</thead>
|
| 230 |
<tbody>
|
| 231 |
<tr class="next">
|
| 232 |
-
<td
|
| 233 |
-
<td
|
| 234 |
-
<td
|
| 235 |
-
<td
|
| 236 |
-
<td
|
| 237 |
</tr>
|
| 238 |
-
<tr
|
| 239 |
-
<td
|
| 240 |
-
<td
|
| 241 |
-
<td
|
| 242 |
-
<td
|
| 243 |
-
<td
|
| 244 |
</tr>
|
| 245 |
<tr>
|
| 246 |
-
<td
|
| 247 |
-
<td
|
| 248 |
-
<td
|
| 249 |
-
<td
|
| 250 |
-
<td
|
| 251 |
</tr>
|
| 252 |
<tr>
|
| 253 |
-
<td
|
| 254 |
-
<td
|
| 255 |
-
<td
|
| 256 |
-
<td
|
| 257 |
-
<td
|
| 258 |
</tr>
|
| 259 |
</tbody>
|
| 260 |
</table>
|
|
|
|
| 149 |
|
| 150 |
---
|
| 151 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
# Our Next 1B and Next 4B models are leading to all of the tiny models in benchmarks.
|
| 153 |
|
| 154 |
<table>
|
|
|
|
| 163 |
</thead>
|
| 164 |
<tbody>
|
| 165 |
<tr class="next">
|
| 166 |
+
<td data-label="Model">Next 4B preview</td>
|
| 167 |
<td data-label="MMLU (5-shot) %">84.6</td>
|
| 168 |
<td data-label="MMLU-Pro %">66.9</td>
|
| 169 |
<td data-label="GSM8K %">82.7</td>
|
| 170 |
<td data-label="MATH %"><strong>70.5</strong></td>
|
| 171 |
</tr>
|
| 172 |
<tr class="next">
|
| 173 |
+
<td data-label="Model">Next 1B</td>
|
| 174 |
<td data-label="MMLU (5-shot) %"><strong>87.3</strong></td>
|
| 175 |
<td data-label="MMLU-Pro %"><strong>69.2</strong></td>
|
| 176 |
<td data-label="GSM8K %"><strong>90.5</strong></td>
|
|
|
|
| 208 |
</thead>
|
| 209 |
<tbody>
|
| 210 |
<tr class="next">
|
| 211 |
+
<td><strong>Next 14B (Thinking)</strong></td>
|
| 212 |
+
<td><strong>94.6</strong></td>
|
| 213 |
+
<td><strong>93.2</strong></td>
|
| 214 |
+
<td><strong>98.8</strong></td>
|
| 215 |
+
<td>92.7</td>
|
| 216 |
</tr>
|
| 217 |
+
<tr>
|
| 218 |
+
<td>Next 12B</td>
|
| 219 |
+
<td>92.7</td>
|
| 220 |
+
<td>84.4</td>
|
| 221 |
+
<td>95.3</td>
|
| 222 |
+
<td>87.2</td>
|
| 223 |
</tr>
|
| 224 |
<tr>
|
| 225 |
+
<td>GPT-5</td>
|
| 226 |
+
<td>92.5</td>
|
| 227 |
+
<td>87.0</td>
|
| 228 |
+
<td>98.4</td>
|
| 229 |
+
<td><strong>96.0</strong></td>
|
| 230 |
</tr>
|
| 231 |
<tr>
|
| 232 |
+
<td>Claude Opus 4.1 (Thinking)</td>
|
| 233 |
+
<td>~92.0</td>
|
| 234 |
+
<td>87.8</td>
|
| 235 |
+
<td>84.7</td>
|
| 236 |
+
<td>95.4</td>
|
| 237 |
</tr>
|
| 238 |
</tbody>
|
| 239 |
</table>
|