Image-Text-to-Text
Transformers
Safetensors
GGUF
gemma3
any-to-any
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
|
@@ -169,23 +169,23 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 169 |
<tbody>
|
| 170 |
<tr class="next">
|
| 171 |
<td data-label="Model">Next 4B preview <em>Version s325</em></td>
|
| 172 |
-
<td data-label="MMLU (5-shot) %">84.
|
| 173 |
-
<td data-label="MMLU-Pro %">66.
|
| 174 |
<td data-label="GSM8K %">82.7</td>
|
| 175 |
-
<td data-label="MATH %">70.5</td>
|
| 176 |
</tr>
|
| 177 |
<tr class="next">
|
| 178 |
<td data-label="Model">Next 1B <em>Version t327</em></td>
|
| 179 |
-
<td data-label="MMLU (5-shot) %"><strong>
|
| 180 |
-
<td data-label="MMLU-Pro %"><strong>69.
|
| 181 |
-
<td data-label="GSM8K %"><strong>
|
| 182 |
-
<td data-label="MATH %"
|
| 183 |
</tr>
|
| 184 |
<tr>
|
| 185 |
<td data-label="Model">Qwen 3 0.6B</td>
|
| 186 |
<td data-label="MMLU (5-shot) %">52.81</td>
|
| 187 |
-
<td data-label="MMLU-Pro %">37.
|
| 188 |
-
<td data-label="GSM8K %">60.
|
| 189 |
<td data-label="MATH %">20.5</td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
|
@@ -197,9 +197,9 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 197 |
</tr>
|
| 198 |
<tr class="turkish">
|
| 199 |
<td data-label="Model">Kumru 7B</td>
|
| 200 |
-
<td data-label="MMLU (5-shot) %">30.
|
| 201 |
-
<td data-label="MMLU-Pro %">28.
|
| 202 |
-
<td data-label="GSM8K %"
|
| 203 |
<td data-label="MATH %">-</td>
|
| 204 |
</tr>
|
| 205 |
</tbody>
|
|
@@ -221,15 +221,15 @@ This model is ideal for **researchers, developers, and organizations** who need
|
|
| 221 |
<tbody>
|
| 222 |
<tr class="next">
|
| 223 |
<td data-label="Model">Next Z1 <em>Version l294</em></td>
|
| 224 |
-
<td data-label="MMLU (5-shot) %"><strong>97.
|
| 225 |
<td data-label="MMLU-Pro %"><strong>94.2</strong></td>
|
| 226 |
<td data-label="GSM8K %">97.7</td>
|
| 227 |
-
<td data-label="MATH %">93.
|
| 228 |
</tr>
|
| 229 |
<tr class="next">
|
| 230 |
<td data-label="Model">Next Z1 <em>Version l294</em> (no tool)</td>
|
| 231 |
<td data-label="MMLU (5-shot) %">94.7</td>
|
| 232 |
-
<td data-label="MMLU-Pro %">90.
|
| 233 |
<td data-label="GSM8K %">94.5</td>
|
| 234 |
<td data-label="MATH %">88.7</td>
|
| 235 |
</tr>
|
|
|
|
| 169 |
<tbody>
|
| 170 |
<tr class="next">
|
| 171 |
<td data-label="Model">Next 4B preview <em>Version s325</em></td>
|
| 172 |
+
<td data-label="MMLU (5-shot) %">84.6</td>
|
| 173 |
+
<td data-label="MMLU-Pro %">66.9</td>
|
| 174 |
<td data-label="GSM8K %">82.7</td>
|
| 175 |
+
<td data-label="MATH %"><strong>70.5</strong></td>
|
| 176 |
</tr>
|
| 177 |
<tr class="next">
|
| 178 |
<td data-label="Model">Next 1B <em>Version t327</em></td>
|
| 179 |
+
<td data-label="MMLU (5-shot) %"><strong>87.3</strong></td>
|
| 180 |
+
<td data-label="MMLU-Pro %"><strong>69.2</strong></td>
|
| 181 |
+
<td data-label="GSM8K %"><strong>90.5</strong></td>
|
| 182 |
+
<td data-label="MATH %">70.1</td>
|
| 183 |
</tr>
|
| 184 |
<tr>
|
| 185 |
<td data-label="Model">Qwen 3 0.6B</td>
|
| 186 |
<td data-label="MMLU (5-shot) %">52.81</td>
|
| 187 |
+
<td data-label="MMLU-Pro %">37.6</td>
|
| 188 |
+
<td data-label="GSM8K %">60.7</td>
|
| 189 |
<td data-label="MATH %">20.5</td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
|
|
|
| 197 |
</tr>
|
| 198 |
<tr class="turkish">
|
| 199 |
<td data-label="Model">Kumru 7B</td>
|
| 200 |
+
<td data-label="MMLU (5-shot) %">30.7</td>
|
| 201 |
+
<td data-label="MMLU-Pro %">28.6</td>
|
| 202 |
+
<td data-label="GSM8K %">15.38</td>
|
| 203 |
<td data-label="MATH %">-</td>
|
| 204 |
</tr>
|
| 205 |
</tbody>
|
|
|
|
| 221 |
<tbody>
|
| 222 |
<tr class="next">
|
| 223 |
<td data-label="Model">Next Z1 <em>Version l294</em></td>
|
| 224 |
+
<td data-label="MMLU (5-shot) %"><strong>97.3</strong></td>
|
| 225 |
<td data-label="MMLU-Pro %"><strong>94.2</strong></td>
|
| 226 |
<td data-label="GSM8K %">97.7</td>
|
| 227 |
+
<td data-label="MATH %">93.2</td>
|
| 228 |
</tr>
|
| 229 |
<tr class="next">
|
| 230 |
<td data-label="Model">Next Z1 <em>Version l294</em> (no tool)</td>
|
| 231 |
<td data-label="MMLU (5-shot) %">94.7</td>
|
| 232 |
+
<td data-label="MMLU-Pro %">90.1</td>
|
| 233 |
<td data-label="GSM8K %">94.5</td>
|
| 234 |
<td data-label="MATH %">88.7</td>
|
| 235 |
</tr>
|