summaryrefslogtreecommitdiff
path: root/docs/docs/reference/Models/hf_inference_api.md
diff options
context:
space:
mode:
Diffstat (limited to 'docs/docs/reference/Models/hf_inference_api.md')
-rw-r--r--docs/docs/reference/Models/hf_inference_api.md2
1 files changed, 1 insertions, 1 deletions
diff --git a/docs/docs/reference/Models/hf_inference_api.md b/docs/docs/reference/Models/hf_inference_api.md
index 605813be..e3f1ed7c 100644
--- a/docs/docs/reference/Models/hf_inference_api.md
+++ b/docs/docs/reference/Models/hf_inference_api.md
@@ -26,4 +26,4 @@ config = ContinueConfig(
### Inherited Properties
-<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the HuggingFaceInferenceAPI class)&quot;, &quot;default&quot;: &quot;Hugging Face Inference API&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="Hugging Face Inference API"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/> \ No newline at end of file
+<ClassPropertyRef name='title' details='{&quot;title&quot;: &quot;Title&quot;, &quot;description&quot;: &quot;A title that will identify this model in the model selection dropdown&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='system_message' details='{&quot;title&quot;: &quot;System Message&quot;, &quot;description&quot;: &quot;A system message that will always be followed by the LLM&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='context_length' details='{&quot;title&quot;: &quot;Context Length&quot;, &quot;description&quot;: &quot;The maximum context length of the LLM in tokens, as counted by count_tokens.&quot;, &quot;default&quot;: 2048, &quot;type&quot;: &quot;integer&quot;}' required={false} default="2048"/><ClassPropertyRef name='unique_id' details='{&quot;title&quot;: &quot;Unique Id&quot;, &quot;description&quot;: &quot;The unique ID of the user.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/><ClassPropertyRef name='model' details='{&quot;title&quot;: &quot;Model&quot;, &quot;description&quot;: &quot;The name of the model to use (optional for the HuggingFaceInferenceAPI class)&quot;, &quot;default&quot;: &quot;Hugging Face Inference API&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default="Hugging Face Inference API"/><ClassPropertyRef name='timeout' details='{&quot;title&quot;: &quot;Timeout&quot;, &quot;description&quot;: &quot;Set the timeout for each request to the LLM. If you are running a local LLM that takes a while to respond, you might want to set this to avoid timeouts.&quot;, &quot;default&quot;: 300, &quot;type&quot;: &quot;integer&quot;}' required={false} default="300"/><ClassPropertyRef name='verify_ssl' details='{&quot;title&quot;: &quot;Verify Ssl&quot;, &quot;description&quot;: &quot;Whether to verify SSL certificates for requests.&quot;, &quot;type&quot;: &quot;boolean&quot;}' required={false} default=""/><ClassPropertyRef name='prompt_templates' details='{&quot;title&quot;: &quot;Prompt Templates&quot;, &quot;description&quot;: &quot;A dictionary of prompt templates that can be used to customize the behavior of the LLM in certain situations. For example, set the \&quot;edit\&quot; key in order to change the prompt that is used for the /edit slash command. Each value in the dictionary is a string templated in mustache syntax, and filled in at runtime with the variables specific to the situation. See the documentation for more information.&quot;, &quot;default&quot;: {&quot;edit&quot;: &quot;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&quot;}, &quot;type&quot;: &quot;object&quot;}' required={false} default="{&#x27;edit&#x27;: &#x27;[INST] Consider the following code:\n```\n{{code_to_edit}}\n```\nEdit the code to perfectly satisfy the following user request:\n{{user_input}}\nOutput nothing except for the code. No code block, no English explanation, no start/end tags.\n[/INST]&#x27;}"/><ClassPropertyRef name='api_key' details='{&quot;title&quot;: &quot;Api Key&quot;, &quot;description&quot;: &quot;The API key for the LLM provider.&quot;, &quot;type&quot;: &quot;string&quot;}' required={false} default=""/> \ No newline at end of file