Skip to content

Commit 670a1b3

Browse files
abetlenabetlen
committed
Deployed b121b7c with MkDocs version: 1.4.2
1 parent e551973 commit 670a1b3

File tree

2 files changed

+18
-18
lines changed

2 files changed

+18
-18
lines changed

‎index.html

Lines changed: 18 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1016,13 +1016,13 @@ <h2 id="llama_cpp.Llama" class="doc doc-heading">
10161016
</span><span id="__span-0-24"><a id="__codelineno-0-24" name="__codelineno-0-24"></a><span class="w"> </span><span class="sd">&quot;&quot;&quot;Load a llama.cpp model from `model_path`.</span>
10171017
</span><span id="__span-0-25"><a id="__codelineno-0-25" name="__codelineno-0-25"></a>
10181018
</span><span id="__span-0-26"><a id="__codelineno-0-26" name="__codelineno-0-26"></a><span class="sd"> Args:</span>
1019-
</span><span id="__span-0-27"><a id="__codelineno-0-27" name="__codelineno-0-27"></a><span class="sd"> model_path: Path to the model directory.</span>
1020-
</span><span id="__span-0-28"><a id="__codelineno-0-28" name="__codelineno-0-28"></a><span class="sd"> n_ctx: Number of tokens to keep in memory.</span>
1019+
</span><span id="__span-0-27"><a id="__codelineno-0-27" name="__codelineno-0-27"></a><span class="sd"> model_path: Path to the model.</span>
1020+
</span><span id="__span-0-28"><a id="__codelineno-0-28" name="__codelineno-0-28"></a><span class="sd"> n_ctx: Maximum context size.</span>
10211021
</span><span id="__span-0-29"><a id="__codelineno-0-29" name="__codelineno-0-29"></a><span class="sd"> n_parts: Number of parts to split the model into. If -1, the number of parts is automatically determined.</span>
1022-
</span><span id="__span-0-30"><a id="__codelineno-0-30" name="__codelineno-0-30"></a><span class="sd"> seed: Random seed.</span>
1023-
</span><span id="__span-0-31"><a id="__codelineno-0-31" name="__codelineno-0-31"></a><span class="sd"> f16_kv: Use half-precision for key/value matrices.</span>
1024-
</span><span id="__span-0-32"><a id="__codelineno-0-32" name="__codelineno-0-32"></a><span class="sd"> logits_all: Return logits for all tokens, not just the vocabulary.</span>
1025-
</span><span id="__span-0-33"><a id="__codelineno-0-33" name="__codelineno-0-33"></a><span class="sd"> vocab_only: Only use tokens in the vocabulary.</span>
1022+
</span><span id="__span-0-30"><a id="__codelineno-0-30" name="__codelineno-0-30"></a><span class="sd"> seed: Random seed. 0 for random.</span>
1023+
</span><span id="__span-0-31"><a id="__codelineno-0-31" name="__codelineno-0-31"></a><span class="sd"> f16_kv: Use half-precision for key/value cache.</span>
1024+
</span><span id="__span-0-32"><a id="__codelineno-0-32" name="__codelineno-0-32"></a><span class="sd"> logits_all: Return logits for all tokens, not just the last token.</span>
1025+
</span><span id="__span-0-33"><a id="__codelineno-0-33" name="__codelineno-0-33"></a><span class="sd"> vocab_only: Only load the vocabulary no weights.</span>
10261026
</span><span id="__span-0-34"><a id="__codelineno-0-34" name="__codelineno-0-34"></a><span class="sd"> n_threads: Number of threads to use. If None, the number of threads is automatically determined.</span>
10271027
</span><span id="__span-0-35"><a id="__codelineno-0-35" name="__codelineno-0-35"></a>
10281028
</span><span id="__span-0-36"><a id="__codelineno-0-36" name="__codelineno-0-36"></a><span class="sd"> Raises:</span>
@@ -1244,7 +1244,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
12441244
<td>
12451245
<code>str</code>
12461246
</td>
1247-
<td><p>Path to the model directory.</p></td>
1247+
<td><p>Path to the model.</p></td>
12481248
<td>
12491249
<em>required</em>
12501250
</td>
@@ -1254,7 +1254,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
12541254
<td>
12551255
<code>int</code>
12561256
</td>
1257-
<td><p>Number of tokens to keep in memory.</p></td>
1257+
<td><p>Maximum context size.</p></td>
12581258
<td>
12591259
<code>512</code>
12601260
</td>
@@ -1274,7 +1274,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
12741274
<td>
12751275
<code>int</code>
12761276
</td>
1277-
<td><p>Random seed.</p></td>
1277+
<td><p>Random seed. 0 for random.</p></td>
12781278
<td>
12791279
<code>1337</code>
12801280
</td>
@@ -1284,7 +1284,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
12841284
<td>
12851285
<code>bool</code>
12861286
</td>
1287-
<td><p>Use half-precision for key/value matrices.</p></td>
1287+
<td><p>Use half-precision for key/value cache.</p></td>
12881288
<td>
12891289
<code>False</code>
12901290
</td>
@@ -1294,7 +1294,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
12941294
<td>
12951295
<code>bool</code>
12961296
</td>
1297-
<td><p>Return logits for all tokens, not just the vocabulary.</p></td>
1297+
<td><p>Return logits for all tokens, not just the last token.</p></td>
12981298
<td>
12991299
<code>False</code>
13001300
</td>
@@ -1304,7 +1304,7 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
13041304
<td>
13051305
<code>bool</code>
13061306
</td>
1307-
<td><p>Only use tokens in the vocabulary.</p></td>
1307+
<td><p>Only load the vocabulary no weights.</p></td>
13081308
<td>
13091309
<code>False</code>
13101310
</td>
@@ -1425,13 +1425,13 @@ <h3 id="llama_cpp.llama.Llama.__init__" class="doc doc-heading">
14251425
</span><span id="__span-0-24"><a id="__codelineno-0-24" name="__codelineno-0-24"></a><span class="w"> </span><span class="sd">&quot;&quot;&quot;Load a llama.cpp model from `model_path`.</span>
14261426
</span><span id="__span-0-25"><a id="__codelineno-0-25" name="__codelineno-0-25"></a>
14271427
</span><span id="__span-0-26"><a id="__codelineno-0-26" name="__codelineno-0-26"></a><span class="sd"> Args:</span>
1428-
</span><span id="__span-0-27"><a id="__codelineno-0-27" name="__codelineno-0-27"></a><span class="sd"> model_path: Path to the model directory.</span>
1429-
</span><span id="__span-0-28"><a id="__codelineno-0-28" name="__codelineno-0-28"></a><span class="sd"> n_ctx: Number of tokens to keep in memory.</span>
1428+
</span><span id="__span-0-27"><a id="__codelineno-0-27" name="__codelineno-0-27"></a><span class="sd"> model_path: Path to the model.</span>
1429+
</span><span id="__span-0-28"><a id="__codelineno-0-28" name="__codelineno-0-28"></a><span class="sd"> n_ctx: Maximum context size.</span>
14301430
</span><span id="__span-0-29"><a id="__codelineno-0-29" name="__codelineno-0-29"></a><span class="sd"> n_parts: Number of parts to split the model into. If -1, the number of parts is automatically determined.</span>
1431-
</span><span id="__span-0-30"><a id="__codelineno-0-30" name="__codelineno-0-30"></a><span class="sd"> seed: Random seed.</span>
1432-
</span><span id="__span-0-31"><a id="__codelineno-0-31" name="__codelineno-0-31"></a><span class="sd"> f16_kv: Use half-precision for key/value matrices.</span>
1433-
</span><span id="__span-0-32"><a id="__codelineno-0-32" name="__codelineno-0-32"></a><span class="sd"> logits_all: Return logits for all tokens, not just the vocabulary.</span>
1434-
</span><span id="__span-0-33"><a id="__codelineno-0-33" name="__codelineno-0-33"></a><span class="sd"> vocab_only: Only use tokens in the vocabulary.</span>
1431+
</span><span id="__span-0-30"><a id="__codelineno-0-30" name="__codelineno-0-30"></a><span class="sd"> seed: Random seed. 0 for random.</span>
1432+
</span><span id="__span-0-31"><a id="__codelineno-0-31" name="__codelineno-0-31"></a><span class="sd"> f16_kv: Use half-precision for key/value cache.</span>
1433+
</span><span id="__span-0-32"><a id="__codelineno-0-32" name="__codelineno-0-32"></a><span class="sd"> logits_all: Return logits for all tokens, not just the last token.</span>
1434+
</span><span id="__span-0-33"><a id="__codelineno-0-33" name="__codelineno-0-33"></a><span class="sd"> vocab_only: Only load the vocabulary no weights.</span>
14351435
</span><span id="__span-0-34"><a id="__codelineno-0-34" name="__codelineno-0-34"></a><span class="sd"> n_threads: Number of threads to use. If None, the number of threads is automatically determined.</span>
14361436
</span><span id="__span-0-35"><a id="__codelineno-0-35" name="__codelineno-0-35"></a>
14371437
</span><span id="__span-0-36"><a id="__codelineno-0-36" name="__codelineno-0-36"></a><span class="sd"> Raises:</span>

‎sitemap.xml.gz

0 Bytes
Binary file not shown.

0 commit comments

Comments
 (0)