update

lgrando1 · Oct 13, 2024 · 07ca98d · 07ca98d
1 parent 37e4e99
commit 07ca98d
Show file tree

Hide file tree

Showing 21 changed files with 721 additions and 121 deletions.
diff --git a/index.json b/index.json
diff --git a/index.xml b/index.xml
@@ -63,7 +63,16 @@
 &lt;p&gt;&lt;strong&gt;Importante:&lt;/strong&gt; Nunca use LLMs como oráculos ou fontes de informação definitiva; já encontrei vários erros em modelos, tanto online quanto offline. Utilize-os apenas como suporte para suas atividades.&lt;/p&gt;
 &lt;h2 id=&#34;1-no-terminal&#34;&gt;1. No Terminal:&lt;/h2&gt;
 &lt;p&gt;Acesse e utilize um LLM diretamente pelo terminal com o &lt;a href=&#34;https://ollama.com/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Ollama&lt;/a&gt;, aproveitando sua flexibilidade e eficiência. Os links acima ensinam como instalá-lo no &lt;a href=&#34;https://lgrando1.github.io/post/ollamawin/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Windows&lt;/a&gt;, &lt;a href=&#34;https://lgrando1.github.io/post/ollama/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Linux&lt;/a&gt;, &lt;a href=&#34;https://lgrando1.github.io/post/llmandroid/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Android via aplicativo&lt;/a&gt; e &lt;a href=&#34;https://lgrando1.github.io/post/llmtermux&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;via Termux&lt;/a&gt;.&lt;/p&gt;
-&lt;p&gt;
+&lt;p&gt;Alguns comandos úteis:&lt;/p&gt;
+&lt;ol&gt;
+&lt;li&gt;Para listar os modelos baixados na sua máquina:&lt;/li&gt;
+&lt;/ol&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama list
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;ol start=&#34;2&#34;&gt;
+&lt;li&gt;Para rodar um modelo. Caso não tenha o modelo, ele será baixado e ativado localmente:&lt;/li&gt;
+&lt;/ol&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt;
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
 
 
 
@@ -91,16 +100,7 @@
                loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
   &lt;/div&gt;&lt;/figure&gt;
 &lt;/p&gt;
-&lt;p&gt;Alguns comandos úteis:&lt;/p&gt;
-&lt;ol&gt;
-&lt;li&gt;Para listar os modelos baixados na sua máquina:&lt;/li&gt;
-&lt;/ol&gt;
-&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama list
-&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;ol start=&#34;2&#34;&gt;
-&lt;li&gt;Para rodar um modelo. Caso não tenha o modelo, ele será baixado e ativado localmente:&lt;/li&gt;
-&lt;/ol&gt;
-&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt;
-&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Para obter informações sobre a performance do modelo, adicione &lt;code&gt;--verbose&lt;/code&gt; ao final:&lt;/p&gt;
+&lt;p&gt;Para obter informações sobre a performance do modelo, adicione &lt;code&gt;--verbose&lt;/code&gt; ao final:&lt;/p&gt;
 &lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt; --verbose
 &lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
 
@@ -130,9 +130,69 @@
                loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
   &lt;/div&gt;&lt;/figure&gt;
 &lt;/p&gt;
-&lt;p&gt;Para sair do modelo, digite:&lt;/p&gt;
+&lt;p&gt;Para saber qual modelo está rodando no server ollama e se ele está utilizando sua CPU ou GPU&lt;/p&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama ps
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+&lt;figure  &gt;
+  &lt;div class=&#34;d-flex justify-content-center&#34;&gt;
+    &lt;div class=&#34;w-100&#34; &gt;&lt;img alt=&#34;Autocomplete&#34; srcset=&#34;
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp 400w,
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_20819ebbf9f8b4af18075cafc3a5b1bd.webp 760w,
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_1200x1200_fit_q75_h2_lanczos_3.webp 1200w&#34;
+               src=&#34;https://lgrando1.github.io/post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp&#34;
+               width=&#34;760&#34;
+               height=&#34;130&#34;
+               loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
+  &lt;/div&gt;&lt;/figure&gt;
+&lt;/p&gt;
+&lt;p&gt;Para remover um modelo específico&lt;/p&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama rm &amp;lt;modelo&amp;gt;
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Para sair do modelo, digite:&lt;/p&gt;
 &lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;/bye
 &lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;ou use Control + D.&lt;/p&gt;
+&lt;p&gt;
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+&lt;figure  &gt;
+  &lt;div class=&#34;d-flex justify-content-center&#34;&gt;
+    &lt;div class=&#34;w-100&#34; &gt;&lt;img alt=&#34;Autocomplete&#34; srcset=&#34;
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp 400w,
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_9da8b85500386e73f2fe08cdf0850e21.webp 760w,
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_1200x1200_fit_q75_h2_lanczos_3.webp 1200w&#34;
+               src=&#34;https://lgrando1.github.io/post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp&#34;
+               width=&#34;752&#34;
+               height=&#34;509&#34;
+               loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
+  &lt;/div&gt;&lt;/figure&gt;
+&lt;/p&gt;
 &lt;h2 id=&#34;2-em-uma-interface-gráfica-gui&#34;&gt;2. Em uma Interface Gráfica (GUI):&lt;/h2&gt;
 &lt;p&gt;Neste exemplo, utilizo a interface disponível em &lt;a href=&#34;https://openwebui.com/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;OpenWebUI&lt;/a&gt;, que instalei via &lt;a href=&#34;https://docs.openwebui.com/getting-started/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Docker&lt;/a&gt; para uma experiência mais intuitiva, permitindo fácil alteração e teste de parâmetros do modelo.&lt;/p&gt;
 &lt;p&gt;Após a instalação do OpenWebUI via &lt;a href=&#34;https://docs.openwebui.com/getting-started/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Docker&lt;/a&gt;:&lt;/p&gt;

diff --git a/post/index.xml b/post/index.xml
@@ -63,7 +63,16 @@
 &lt;p&gt;&lt;strong&gt;Importante:&lt;/strong&gt; Nunca use LLMs como oráculos ou fontes de informação definitiva; já encontrei vários erros em modelos, tanto online quanto offline. Utilize-os apenas como suporte para suas atividades.&lt;/p&gt;
 &lt;h2 id=&#34;1-no-terminal&#34;&gt;1. No Terminal:&lt;/h2&gt;
 &lt;p&gt;Acesse e utilize um LLM diretamente pelo terminal com o &lt;a href=&#34;https://ollama.com/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Ollama&lt;/a&gt;, aproveitando sua flexibilidade e eficiência. Os links acima ensinam como instalá-lo no &lt;a href=&#34;https://lgrando1.github.io/post/ollamawin/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Windows&lt;/a&gt;, &lt;a href=&#34;https://lgrando1.github.io/post/ollama/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Linux&lt;/a&gt;, &lt;a href=&#34;https://lgrando1.github.io/post/llmandroid/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Android via aplicativo&lt;/a&gt; e &lt;a href=&#34;https://lgrando1.github.io/post/llmtermux&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;via Termux&lt;/a&gt;.&lt;/p&gt;
-&lt;p&gt;
+&lt;p&gt;Alguns comandos úteis:&lt;/p&gt;
+&lt;ol&gt;
+&lt;li&gt;Para listar os modelos baixados na sua máquina:&lt;/li&gt;
+&lt;/ol&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama list
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;ol start=&#34;2&#34;&gt;
+&lt;li&gt;Para rodar um modelo. Caso não tenha o modelo, ele será baixado e ativado localmente:&lt;/li&gt;
+&lt;/ol&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt;
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
 
 
 
@@ -91,16 +100,7 @@
                loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
   &lt;/div&gt;&lt;/figure&gt;
 &lt;/p&gt;
-&lt;p&gt;Alguns comandos úteis:&lt;/p&gt;
-&lt;ol&gt;
-&lt;li&gt;Para listar os modelos baixados na sua máquina:&lt;/li&gt;
-&lt;/ol&gt;
-&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama list
-&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;ol start=&#34;2&#34;&gt;
-&lt;li&gt;Para rodar um modelo. Caso não tenha o modelo, ele será baixado e ativado localmente:&lt;/li&gt;
-&lt;/ol&gt;
-&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt;
-&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Para obter informações sobre a performance do modelo, adicione &lt;code&gt;--verbose&lt;/code&gt; ao final:&lt;/p&gt;
+&lt;p&gt;Para obter informações sobre a performance do modelo, adicione &lt;code&gt;--verbose&lt;/code&gt; ao final:&lt;/p&gt;
 &lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama run &amp;lt;modelo&amp;gt; --verbose
 &lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
 
@@ -130,9 +130,69 @@
                loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
   &lt;/div&gt;&lt;/figure&gt;
 &lt;/p&gt;
-&lt;p&gt;Para sair do modelo, digite:&lt;/p&gt;
+&lt;p&gt;Para saber qual modelo está rodando no server ollama e se ele está utilizando sua CPU ou GPU&lt;/p&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama ps
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+&lt;figure  &gt;
+  &lt;div class=&#34;d-flex justify-content-center&#34;&gt;
+    &lt;div class=&#34;w-100&#34; &gt;&lt;img alt=&#34;Autocomplete&#34; srcset=&#34;
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp 400w,
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_20819ebbf9f8b4af18075cafc3a5b1bd.webp 760w,
+               /post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_1200x1200_fit_q75_h2_lanczos_3.webp 1200w&#34;
+               src=&#34;https://lgrando1.github.io/post/waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp&#34;
+               width=&#34;760&#34;
+               height=&#34;130&#34;
+               loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
+  &lt;/div&gt;&lt;/figure&gt;
+&lt;/p&gt;
+&lt;p&gt;Para remover um modelo específico&lt;/p&gt;
+&lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;ollama rm &amp;lt;modelo&amp;gt;
+&lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;Para sair do modelo, digite:&lt;/p&gt;
 &lt;div class=&#34;highlight&#34;&gt;&lt;pre tabindex=&#34;0&#34; class=&#34;chroma&#34;&gt;&lt;code class=&#34;language-bash&#34; data-lang=&#34;bash&#34;&gt;&lt;span class=&#34;line&#34;&gt;&lt;span class=&#34;cl&#34;&gt;/bye
 &lt;/span&gt;&lt;/span&gt;&lt;/code&gt;&lt;/pre&gt;&lt;/div&gt;&lt;p&gt;ou use Control + D.&lt;/p&gt;
+&lt;p&gt;
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+&lt;figure  &gt;
+  &lt;div class=&#34;d-flex justify-content-center&#34;&gt;
+    &lt;div class=&#34;w-100&#34; &gt;&lt;img alt=&#34;Autocomplete&#34; srcset=&#34;
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp 400w,
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_9da8b85500386e73f2fe08cdf0850e21.webp 760w,
+               /post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_1200x1200_fit_q75_h2_lanczos_3.webp 1200w&#34;
+               src=&#34;https://lgrando1.github.io/post/waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp&#34;
+               width=&#34;752&#34;
+               height=&#34;509&#34;
+               loading=&#34;lazy&#34; data-zoomable /&gt;&lt;/div&gt;
+  &lt;/div&gt;&lt;/figure&gt;
+&lt;/p&gt;
 &lt;h2 id=&#34;2-em-uma-interface-gráfica-gui&#34;&gt;2. Em uma Interface Gráfica (GUI):&lt;/h2&gt;
 &lt;p&gt;Neste exemplo, utilizo a interface disponível em &lt;a href=&#34;https://openwebui.com/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;OpenWebUI&lt;/a&gt;, que instalei via &lt;a href=&#34;https://docs.openwebui.com/getting-started/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Docker&lt;/a&gt; para uma experiência mais intuitiva, permitindo fácil alteração e teste de parâmetros do modelo.&lt;/p&gt;
 &lt;p&gt;Após a instalação do OpenWebUI via &lt;a href=&#34;https://docs.openwebui.com/getting-started/&#34; target=&#34;_blank&#34; rel=&#34;noopener&#34;&gt;Docker&lt;/a&gt;:&lt;/p&gt;

diff --git a/post/waysllms/16.png b/post/waysllms/16.png
diff --git a/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_105631f103314038b5e018d4fc97c74c.webp b/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_105631f103314038b5e018d4fc97c74c.webp
diff --git a/.../waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_1200x1200_fit_q75_h2_lanczos_3.webp b/.../waysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_1200x1200_fit_q75_h2_lanczos_3.webp
diff --git a/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_20819ebbf9f8b4af18075cafc3a5b1bd.webp b/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_20819ebbf9f8b4af18075cafc3a5b1bd.webp
diff --git a/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp b/...aysllms/16_hucb240043efc8f920ac402efe21df5f6a_21788_59cc00b912e75497022b4b222c6abbf3.webp
diff --git a/post/waysllms/17.png b/post/waysllms/17.png
diff --git a/...waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_1200x1200_fit_q75_h2_lanczos_3.webp b/...waysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_1200x1200_fit_q75_h2_lanczos_3.webp
diff --git a/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_586646911963853a40aa70d53d453b5b.webp b/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_586646911963853a40aa70d53d453b5b.webp
diff --git a/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp b/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_5b37473213458103f1e7cb55919aa796.webp
diff --git a/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_9da8b85500386e73f2fe08cdf0850e21.webp b/...ysllms/17_hu922c4ee3e346a5e7dcc7f6de16ace428_105350_9da8b85500386e73f2fe08cdf0850e21.webp