Text Generation
Transformers
Safetensors
GGUF
gemma3_text
turkish
türkiye
english
ai
lamapi
gemma3
next
next-x1
efficient
open-source
1b
huggingface
large-language-model
llm
causal
transformer
artificial-intelligence
machine-learning
ai-research
natural-language-processing
nlp
finetuned
lightweight
creative
summarization
question-answering
chat-model
generative-ai
optimized-model
unsloth
trl
sft
chemistry
biology
finance
legal
music
art
code
climate
medical
agent
text-generation-inference
conversational
Update README.md
Browse files
README.md
CHANGED
|
@@ -112,23 +112,23 @@ Ideal for **developers, students, and organizations** needing **fast, reliable,
|
|
| 112 |
<tbody>
|
| 113 |
<tr class="next">
|
| 114 |
<td data-label="Model">Next 4B preview <em>Version s325</em></td>
|
| 115 |
-
<td data-label="MMLU (5-shot) %">84.
|
| 116 |
-
<td data-label="MMLU-Pro %">66.
|
| 117 |
<td data-label="GSM8K %">82.7</td>
|
| 118 |
<td data-label="MATH %">70.5</td>
|
| 119 |
</tr>
|
| 120 |
<tr class="next">
|
| 121 |
<td data-label="Model">Next 1B <em>Version t327</em></td>
|
| 122 |
<td data-label="MMLU (5-shot) %"><strong>90.3</strong></td>
|
| 123 |
-
<td data-label="MMLU-Pro %"><strong>69.
|
| 124 |
-
<td data-label="GSM8K %"><strong>91.
|
| 125 |
<td data-label="MATH %"><strong>77.1</strong></td>
|
| 126 |
</tr>
|
| 127 |
<tr>
|
| 128 |
<td data-label="Model">Qwen 3 0.6B</td>
|
| 129 |
<td data-label="MMLU (5-shot) %">52.81</td>
|
| 130 |
-
<td data-label="MMLU-Pro %">37.
|
| 131 |
-
<td data-label="GSM8K %">60.
|
| 132 |
<td data-label="MATH %">20.5</td>
|
| 133 |
</tr>
|
| 134 |
<tr>
|
|
@@ -140,9 +140,9 @@ Ideal for **developers, students, and organizations** needing **fast, reliable,
|
|
| 140 |
</tr>
|
| 141 |
<tr class="turkish">
|
| 142 |
<td data-label="Model">Kumru 7B</td>
|
| 143 |
-
<td data-label="MMLU (5-shot) %">30.
|
| 144 |
-
<td data-label="MMLU-Pro %">28.
|
| 145 |
-
<td data-label="GSM8K %"
|
| 146 |
<td data-label="MATH %">-</td>
|
| 147 |
</tr>
|
| 148 |
</tbody>
|
|
@@ -164,15 +164,15 @@ Ideal for **developers, students, and organizations** needing **fast, reliable,
|
|
| 164 |
<tbody>
|
| 165 |
<tr class="next">
|
| 166 |
<td data-label="Model">Next Z1 <em>Version l294</em></td>
|
| 167 |
-
<td data-label="MMLU (5-shot) %"><strong>97.
|
| 168 |
<td data-label="MMLU-Pro %"><strong>94.2</strong></td>
|
| 169 |
<td data-label="GSM8K %">97.7</td>
|
| 170 |
-
<td data-label="MATH %">93.
|
| 171 |
</tr>
|
| 172 |
<tr class="next">
|
| 173 |
<td data-label="Model">Next Z1 <em>Version l294</em> (no tool)</td>
|
| 174 |
<td data-label="MMLU (5-shot) %">94.7</td>
|
| 175 |
-
<td data-label="MMLU-Pro %">90.
|
| 176 |
<td data-label="GSM8K %">94.5</td>
|
| 177 |
<td data-label="MATH %">88.7</td>
|
| 178 |
</tr>
|
|
|
|
| 112 |
<tbody>
|
| 113 |
<tr class="next">
|
| 114 |
<td data-label="Model">Next 4B preview <em>Version s325</em></td>
|
| 115 |
+
<td data-label="MMLU (5-shot) %">84.6</td>
|
| 116 |
+
<td data-label="MMLU-Pro %">66.9</td>
|
| 117 |
<td data-label="GSM8K %">82.7</td>
|
| 118 |
<td data-label="MATH %">70.5</td>
|
| 119 |
</tr>
|
| 120 |
<tr class="next">
|
| 121 |
<td data-label="Model">Next 1B <em>Version t327</em></td>
|
| 122 |
<td data-label="MMLU (5-shot) %"><strong>90.3</strong></td>
|
| 123 |
+
<td data-label="MMLU-Pro %"><strong>69.2</strong></td>
|
| 124 |
+
<td data-label="GSM8K %"><strong>91.5</strong></td>
|
| 125 |
<td data-label="MATH %"><strong>77.1</strong></td>
|
| 126 |
</tr>
|
| 127 |
<tr>
|
| 128 |
<td data-label="Model">Qwen 3 0.6B</td>
|
| 129 |
<td data-label="MMLU (5-shot) %">52.81</td>
|
| 130 |
+
<td data-label="MMLU-Pro %">37.6</td>
|
| 131 |
+
<td data-label="GSM8K %">60.7</td>
|
| 132 |
<td data-label="MATH %">20.5</td>
|
| 133 |
</tr>
|
| 134 |
<tr>
|
|
|
|
| 140 |
</tr>
|
| 141 |
<tr class="turkish">
|
| 142 |
<td data-label="Model">Kumru 7B</td>
|
| 143 |
+
<td data-label="MMLU (5-shot) %">30.7</td>
|
| 144 |
+
<td data-label="MMLU-Pro %">28.6</td>
|
| 145 |
+
<td data-label="GSM8K %">15.38</td>
|
| 146 |
<td data-label="MATH %">-</td>
|
| 147 |
</tr>
|
| 148 |
</tbody>
|
|
|
|
| 164 |
<tbody>
|
| 165 |
<tr class="next">
|
| 166 |
<td data-label="Model">Next Z1 <em>Version l294</em></td>
|
| 167 |
+
<td data-label="MMLU (5-shot) %"><strong>97.3</strong></td>
|
| 168 |
<td data-label="MMLU-Pro %"><strong>94.2</strong></td>
|
| 169 |
<td data-label="GSM8K %">97.7</td>
|
| 170 |
+
<td data-label="MATH %">93.2</td>
|
| 171 |
</tr>
|
| 172 |
<tr class="next">
|
| 173 |
<td data-label="Model">Next Z1 <em>Version l294</em> (no tool)</td>
|
| 174 |
<td data-label="MMLU (5-shot) %">94.7</td>
|
| 175 |
+
<td data-label="MMLU-Pro %">90.1</td>
|
| 176 |
<td data-label="GSM8K %">94.5</td>
|
| 177 |
<td data-label="MATH %">88.7</td>
|
| 178 |
</tr>
|