@@ -3190,10 +3190,10 @@ <h2 id="llama_cpp.Llama" class="doc doc-heading">
3190
3190
</span><span id="__span-0-446"><a id="__codelineno-0-446" name="__codelineno-0-446"></a> <span class="k">def</span> <span class="nf">generate</span><span class="p">(</span>
3191
3191
</span><span id="__span-0-447"><a id="__codelineno-0-447" name="__codelineno-0-447"></a> <span class="bp">self</span><span class="p">,</span>
3192
3192
</span><span id="__span-0-448"><a id="__codelineno-0-448" name="__codelineno-0-448"></a> <span class="n">tokens</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">llama_cpp</span><span class="o">.</span><span class="n">llama_token</span><span class="p">],</span>
3193
- </span><span id="__span-0-449"><a id="__codelineno-0-449" name="__codelineno-0-449"></a> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
3194
- </span><span id="__span-0-450"><a id="__codelineno-0-450" name="__codelineno-0-450"></a> <span class="n">top_p</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
3195
- </span><span id="__span-0-451"><a id="__codelineno-0-451" name="__codelineno-0-451"></a> <span class="n">temp</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
3196
- </span><span id="__span-0-452"><a id="__codelineno-0-452" name="__codelineno-0-452"></a> <span class="n">repeat_penalty</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
3193
+ </span><span id="__span-0-449"><a id="__codelineno-0-449" name="__codelineno-0-449"></a> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">40</span> <span class="p">,</span>
3194
+ </span><span id="__span-0-450"><a id="__codelineno-0-450" name="__codelineno-0-450"></a> <span class="n">top_p</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.95</span> <span class="p">,</span>
3195
+ </span><span id="__span-0-451"><a id="__codelineno-0-451" name="__codelineno-0-451"></a> <span class="n">temp</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.80</span> <span class="p">,</span>
3196
+ </span><span id="__span-0-452"><a id="__codelineno-0-452" name="__codelineno-0-452"></a> <span class="n">repeat_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.1</span> <span class="p">,</span>
3197
3197
</span><span id="__span-0-453"><a id="__codelineno-0-453" name="__codelineno-0-453"></a> <span class="n">reset</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
3198
3198
</span><span id="__span-0-454"><a id="__codelineno-0-454" name="__codelineno-0-454"></a> <span class="n">frequency_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
3199
3199
</span><span id="__span-0-455"><a id="__codelineno-0-455" name="__codelineno-0-455"></a> <span class="n">presence_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
@@ -4933,7 +4933,7 @@ <h3 id="llama_cpp.llama.Llama.sample" class="doc doc-heading">
4933
4933
4934
4934
4935
4935
<h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
4936
- <code class="highlight language-python"><span class="n">generate</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="n">top_k</span><span class="p">,</span> <span class="n">top_p</span><span class="p">,</span> <span class="n">temp</span><span class="p">,</span> <span class="n">repeat_penalty</span><span class="p">,</span> <span class="n">reset</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">frequency_penalty</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">presence_penalty</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">tfs_z</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">mirostat_mode</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">mirostat_tau</span><span class="o">=</span><span class="mf">5.0</span><span class="p">,</span> <span class="n">mirostat_eta</span><span class="o">=</span><span class="mf">0.1</span><span class="p">)</span></code>
4936
+ <code class="highlight language-python"><span class="n">generate</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="n">top_k</span><span class="o">=</span><span class="mi">40</span><span class="p">,</span> <span class="n">top_p</span><span class="o">=</span><span class="mf">0.95</span><span class="p">,</span> <span class="n">temp</span><span class="o">=</span><span class="mf">0.8</span><span class="p">,</span> <span class="n">repeat_penalty</span><span class="o">=</span><span class="mf">1.1</span><span class="p">,</span> <span class="n">reset</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">frequency_penalty</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">presence_penalty</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span> <span class="n">tfs_z</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span> <span class="n">mirostat_mode</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">mirostat_tau</span><span class="o">=</span><span class="mf">5.0</span><span class="p">,</span> <span class="n">mirostat_eta</span><span class="o">=</span><span class="mf">0.1</span><span class="p">)</span></code>
4937
4937
4938
4938
</h3>
4939
4939
@@ -4977,7 +4977,7 @@ <h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
4977
4977
</td>
4978
4978
<td><p>The top-k sampling parameter.</p></td>
4979
4979
<td>
4980
- <em>required</em >
4980
+ <code>40</code >
4981
4981
</td>
4982
4982
</tr>
4983
4983
<tr>
@@ -4987,7 +4987,7 @@ <h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
4987
4987
</td>
4988
4988
<td><p>The top-p sampling parameter.</p></td>
4989
4989
<td>
4990
- <em>required</em >
4990
+ <code>0.95</code >
4991
4991
</td>
4992
4992
</tr>
4993
4993
<tr>
@@ -4997,7 +4997,7 @@ <h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
4997
4997
</td>
4998
4998
<td><p>The temperature parameter.</p></td>
4999
4999
<td>
5000
- <em>required</em >
5000
+ <code>0.8</code >
5001
5001
</td>
5002
5002
</tr>
5003
5003
<tr>
@@ -5007,7 +5007,7 @@ <h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
5007
5007
</td>
5008
5008
<td><p>The repeat penalty parameter.</p></td>
5009
5009
<td>
5010
- <em>required</em >
5010
+ <code>1.1</code >
5011
5011
</td>
5012
5012
</tr>
5013
5013
<tr>
@@ -5123,10 +5123,10 @@ <h3 id="llama_cpp.llama.Llama.generate" class="doc doc-heading">
5123
5123
<span class="normal"><a href="#__codelineno-0-523">523</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-446"><a id="__codelineno-0-446" name="__codelineno-0-446"></a><span class="k">def</span> <span class="nf">generate</span><span class="p">(</span>
5124
5124
</span><span id="__span-0-447"><a id="__codelineno-0-447" name="__codelineno-0-447"></a> <span class="bp">self</span><span class="p">,</span>
5125
5125
</span><span id="__span-0-448"><a id="__codelineno-0-448" name="__codelineno-0-448"></a> <span class="n">tokens</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">llama_cpp</span><span class="o">.</span><span class="n">llama_token</span><span class="p">],</span>
5126
- </span><span id="__span-0-449"><a id="__codelineno-0-449" name="__codelineno-0-449"></a> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
5127
- </span><span id="__span-0-450"><a id="__codelineno-0-450" name="__codelineno-0-450"></a> <span class="n">top_p</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
5128
- </span><span id="__span-0-451"><a id="__codelineno-0-451" name="__codelineno-0-451"></a> <span class="n">temp</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
5129
- </span><span id="__span-0-452"><a id="__codelineno-0-452" name="__codelineno-0-452"></a> <span class="n">repeat_penalty</span><span class="p">:</span> <span class="nb">float</span><span class="p">,</span>
5126
+ </span><span id="__span-0-449"><a id="__codelineno-0-449" name="__codelineno-0-449"></a> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">40</span> <span class="p">,</span>
5127
+ </span><span id="__span-0-450"><a id="__codelineno-0-450" name="__codelineno-0-450"></a> <span class="n">top_p</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.95</span> <span class="p">,</span>
5128
+ </span><span id="__span-0-451"><a id="__codelineno-0-451" name="__codelineno-0-451"></a> <span class="n">temp</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.80</span> <span class="p">,</span>
5129
+ </span><span id="__span-0-452"><a id="__codelineno-0-452" name="__codelineno-0-452"></a> <span class="n">repeat_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.1</span> <span class="p">,</span>
5130
5130
</span><span id="__span-0-453"><a id="__codelineno-0-453" name="__codelineno-0-453"></a> <span class="n">reset</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">,</span>
5131
5131
</span><span id="__span-0-454"><a id="__codelineno-0-454" name="__codelineno-0-454"></a> <span class="n">frequency_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
5132
5132
</span><span id="__span-0-455"><a id="__codelineno-0-455" name="__codelineno-0-455"></a> <span class="n">presence_penalty</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
0 commit comments