Built site for gh-pages
This commit is contained in:
@@ -714,36 +714,37 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<span id="cb1-406"><a href="#cb1-406" aria-hidden="true" tabindex="-1"></a><span class="co"> # bos_token: "<s>"</span></span>
|
||||
<span id="cb1-407"><a href="#cb1-407" aria-hidden="true" tabindex="-1"></a><span class="co"> # eos_token: "</s>"</span></span>
|
||||
<span id="cb1-408"><a href="#cb1-408" aria-hidden="true" tabindex="-1"></a><span class="co"> # unk_token: "<unk>"</span></span>
|
||||
<span id="cb1-409"><a href="#cb1-409" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-410"><a href="#cb1-410" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
|
||||
<span id="cb1-411"><a href="#cb1-411" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb1-412"><a href="#cb1-412" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-413"><a href="#cb1-413" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
|
||||
<span id="cb1-414"><a href="#cb1-414" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
|
||||
<span id="cb1-415"><a href="#cb1-415" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||||
<span id="cb1-416"><a href="#cb1-416" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-417"><a href="#cb1-417" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
|
||||
<span id="cb1-418"><a href="#cb1-418" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
|
||||
<span id="cb1-419"><a href="#cb1-419" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-420"><a href="#cb1-420" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
|
||||
<span id="cb1-421"><a href="#cb1-421" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
|
||||
<span id="cb1-422"><a href="#cb1-422" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
|
||||
<span id="cb1-423"><a href="#cb1-423" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
|
||||
<span id="cb1-424"><a href="#cb1-424" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-425"><a href="#cb1-425" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-426"><a href="#cb1-426" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
|
||||
<span id="cb1-427"><a href="#cb1-427" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-428"><a href="#cb1-428" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
|
||||
<span id="cb1-429"><a href="#cb1-429" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
|
||||
<span id="cb1-430"><a href="#cb1-430" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-431"><a href="#cb1-431" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
|
||||
<span id="cb1-432"><a href="#cb1-432" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
|
||||
<span id="cb1-433"><a href="#cb1-433" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-434"><a href="#cb1-434" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
|
||||
<span id="cb1-435"><a href="#cb1-435" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
|
||||
<span id="cb1-436"><a href="#cb1-436" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-437"><a href="#cb1-437" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
|
||||
<span id="cb1-438"><a href="#cb1-438" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<span id="cb1-409"><a href="#cb1-409" aria-hidden="true" tabindex="-1"></a><span class="co"> # pad_token: "[PAD]"</span></span>
|
||||
<span id="cb1-410"><a href="#cb1-410" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-411"><a href="#cb1-411" aria-hidden="true" tabindex="-1"></a><span class="co"># Add extra tokens.</span></span>
|
||||
<span id="cb1-412"><a href="#cb1-412" aria-hidden="true" tabindex="-1"></a><span class="fu">tokens</span><span class="kw">:</span></span>
|
||||
<span id="cb1-413"><a href="#cb1-413" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-414"><a href="#cb1-414" aria-hidden="true" tabindex="-1"></a><span class="co"># FSDP</span></span>
|
||||
<span id="cb1-415"><a href="#cb1-415" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp</span><span class="kw">:</span></span>
|
||||
<span id="cb1-416"><a href="#cb1-416" aria-hidden="true" tabindex="-1"></a><span class="fu">fsdp_config</span><span class="kw">:</span></span>
|
||||
<span id="cb1-417"><a href="#cb1-417" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-418"><a href="#cb1-418" aria-hidden="true" tabindex="-1"></a><span class="co"># Deepspeed config path. e.g., deepspeed_configs/zero3.json</span></span>
|
||||
<span id="cb1-419"><a href="#cb1-419" aria-hidden="true" tabindex="-1"></a><span class="fu">deepspeed</span><span class="kw">:</span></span>
|
||||
<span id="cb1-420"><a href="#cb1-420" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-421"><a href="#cb1-421" aria-hidden="true" tabindex="-1"></a><span class="co"># Advanced DDP Arguments</span></span>
|
||||
<span id="cb1-422"><a href="#cb1-422" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_timeout</span><span class="kw">:</span></span>
|
||||
<span id="cb1-423"><a href="#cb1-423" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_bucket_cap_mb</span><span class="kw">:</span></span>
|
||||
<span id="cb1-424"><a href="#cb1-424" aria-hidden="true" tabindex="-1"></a><span class="fu">ddp_broadcast_buffers</span><span class="kw">:</span></span>
|
||||
<span id="cb1-425"><a href="#cb1-425" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-426"><a href="#cb1-426" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-427"><a href="#cb1-427" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span></span>
|
||||
<span id="cb1-428"><a href="#cb1-428" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-429"><a href="#cb1-429" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to HF dataset for type: 'completion' for streaming instead of pre-tokenize</span></span>
|
||||
<span id="cb1-430"><a href="#cb1-430" aria-hidden="true" tabindex="-1"></a><span class="fu">pretraining_dataset</span><span class="kw">:</span></span>
|
||||
<span id="cb1-431"><a href="#cb1-431" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-432"><a href="#cb1-432" aria-hidden="true" tabindex="-1"></a><span class="co"># Debug mode</span></span>
|
||||
<span id="cb1-433"><a href="#cb1-433" aria-hidden="true" tabindex="-1"></a><span class="fu">debug</span><span class="kw">:</span></span>
|
||||
<span id="cb1-434"><a href="#cb1-434" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-435"><a href="#cb1-435" aria-hidden="true" tabindex="-1"></a><span class="co"># Seed</span></span>
|
||||
<span id="cb1-436"><a href="#cb1-436" aria-hidden="true" tabindex="-1"></a><span class="fu">seed</span><span class="kw">:</span></span>
|
||||
<span id="cb1-437"><a href="#cb1-437" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-438"><a href="#cb1-438" aria-hidden="true" tabindex="-1"></a><span class="co"># Allow overwrite yml config using from cli</span></span>
|
||||
<span id="cb1-439"><a href="#cb1-439" aria-hidden="true" tabindex="-1"></a><span class="fu">strict</span><span class="kw">:</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -351,7 +351,7 @@ Description
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody class="list">
|
||||
<tr data-index="0" data-listing-file-modified-sort="1713311159149" data-listing-reading-time-sort="1" data-listing-word-count-sort="47" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
|
||||
<tr data-index="0" data-listing-file-modified-sort="1713460832370" data-listing-reading-time-sort="1" data-listing-word-count-sort="47" data-listing-title-sort="Pre-training" data-listing-filename-sort="pretraining.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/pretraining.html" class="title listing-title">Pre-training</a>
|
||||
</td>
|
||||
@@ -359,7 +359,7 @@ Description
|
||||
<span class="listing-description">Data format for a pre-training completion task.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="1" data-listing-file-modified-sort="1713311159149" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
|
||||
<tr data-index="1" data-listing-file-modified-sort="1713460832370" data-listing-reading-time-sort="2" data-listing-word-count-sort="308" data-listing-title-sort="Instruction Tuning" data-listing-filename-sort="inst_tune.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/inst_tune.html" class="title listing-title">Instruction Tuning</a>
|
||||
</td>
|
||||
@@ -367,7 +367,7 @@ Description
|
||||
<span class="listing-description">Instruction tuning formats for supervised fine-tuning.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="2" data-listing-file-modified-sort="1713311159149" data-listing-reading-time-sort="2" data-listing-word-count-sort="235" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
|
||||
<tr data-index="2" data-listing-file-modified-sort="1713460832370" data-listing-reading-time-sort="2" data-listing-word-count-sort="235" data-listing-title-sort="Conversation" data-listing-filename-sort="conversation.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/conversation.html" class="title listing-title">Conversation</a>
|
||||
</td>
|
||||
@@ -375,7 +375,7 @@ Description
|
||||
<span class="listing-description">Conversation format for supervised fine-tuning.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="3" data-listing-file-modified-sort="1713311159149" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
|
||||
<tr data-index="3" data-listing-file-modified-sort="1713460832370" data-listing-reading-time-sort="1" data-listing-word-count-sort="3" data-listing-title-sort="Template-Free" data-listing-filename-sort="template_free.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/template_free.html" class="title listing-title">Template-Free</a>
|
||||
</td>
|
||||
@@ -383,7 +383,7 @@ Description
|
||||
<span class="listing-description">Construct prompts without a template.</span>
|
||||
</td>
|
||||
</tr>
|
||||
<tr data-index="4" data-listing-file-modified-sort="1713311159149" data-listing-reading-time-sort="1" data-listing-word-count-sort="22" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
|
||||
<tr data-index="4" data-listing-file-modified-sort="1713460832370" data-listing-reading-time-sort="1" data-listing-word-count-sort="22" data-listing-title-sort="Custom Pre-Tokenized Dataset" data-listing-filename-sort="tokenized.qmd">
|
||||
<td>
|
||||
<a href="../../docs/dataset-formats/tokenized.html" class="title listing-title">Custom Pre-Tokenized Dataset</a>
|
||||
</td>
|
||||
|
||||
Reference in New Issue
Block a user