Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Notebook fixes for prompt completion #16420

Merged
merged 2 commits into from
Oct 8, 2024
+26 −2
Merged

Notebook fixes for prompt completion #16420

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
452d6fd
docs: add streaming print cell
raspawar Oct 8, 2024
e627f13
docs: add info for arguments
raspawar Oct 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 26 additions & 2 deletions docs/docs/examples/llm/nvidia_text_completion.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,12 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Working with NVIDIA API Catalog"
"## Working with NVIDIA API Catalog\n",
"#### Usage of `use_chat_completions` argument: \n",
"Set None (default) to per-invocation decide on using /chat/completions vs /completions endpoints with query keyword arguments\n",
"\n",
"- set False to universally use /completions endpoint\n",
"- set True to universally use /chat/completions endpoint"
]
},
{
Expand All @@ -113,13 +118,22 @@
"llm = NVIDIA(model=\"bigcode/starcoder2-15b\", use_chat_completions=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Available Models\n",
"\n",
"`is_chat_model` can be used to get available text completion models"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"llm.available_models"
"print([model for model in llm.available_models if model.is_chat_model])"
]
},
{
Expand Down Expand Up @@ -206,6 +220,16 @@
"x = llm.stream_complete(prompt=\"# Reverse string in python:\", max_tokens=512)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"for t in x:\n",
" print(t.delta, end=\"\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
Expand Down
Loading