Skip to content

Commit 05cf9ba

Browse files
sd109sd109
authored
Merge pull request #5 from stackhpc/feat/ui-improvements
Azimuth UI improvements
2 parents 4ad7aa9 + cae797d commit 05cf9ba

File tree

3 files changed

+20
-11
lines changed

3 files changed

+20
-11
lines changed

‎README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ The following is a non-exhaustive list of models which have been tested with thi
4646
- [Mistral 7B Instruct v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
4747
<!-- - [AWQ Quantized Mixtral 8x7B Instruct v0.1](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ) (Not producing output properly) -->
4848

49-
Due to the combination of [components](##Components) used in this app, some HuggingFace models may not work as expected (usually due to the way in which LangChain formats the prompt messages). Any errors when using new model will appear in the pod logs for either the web-app deployment or the backend API deployment.
49+
Due to the combination of [components](##Components) used in this app, some HuggingFace models may not work as expected (usually due to the way in which LangChain formats the prompt messages). Any errors when using new model will appear in the logs for either the web-app pod or the backend API pod. Please open an issue if you would like explicit support for a specific model which is not in the above list.
5050

5151

5252
## Components

‎chart/azimuth-ui.schema.yaml‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,7 @@
11
controls:
22
/huggingface/model:
33
type: TextControl
4+
required: true
45
/huggingface/token:
56
type: TextControl
67
secret: true

‎chart/values.schema.json‎

Lines changed: 18 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -8,12 +8,12 @@
88
"model": {
99
"type": "string",
1010
"title": "Model",
11-
"description": "The HuggingFace model to deploy (Hint: For a simple, lightweight demo try ise-uiuc/Magicoder-S-DS-6.7B)"
11+
"description": "The [HuggingFace model](https://huggingface.co/models) to deploy (see [here](https://github.com/stackhpc/azimuth-llm?tab=readme-ov-file#tested-models) for a list of tested models)."
1212
},
1313
"token": {
1414
"type": "string",
1515
"title": "Access Token",
16-
"description": "The HuggingFace access token to use for installing gated models.",
16+
"description": "A HuggingFace [access token](https://huggingface.co/docs/hub/security-tokens). Only required for [gated models](https://huggingface.co/docs/hub/en/models-gated (e.g. Llama 2).",
1717
"default": ""
1818
}
1919
},
@@ -28,42 +28,50 @@
2828
"model_name": {
2929
"type": "string",
3030
"title": "Model Name",
31-
"description": "Model name supplied to OpenAI client in frontend web app. Should match huggingface.model above."
31+
"description": "Model name supplied to the OpenAI client in frontend web app. Should match huggingface.model above.",
32+
"default": "mistralai/Mistral-7B-Instruct-v0.2"
3233
},
3334
"model_instruction": {
3435
"type": "string",
3536
"title": "Instruction",
36-
"description": "The initial model prompt (i.e. the hidden instructions) to use when generating responses."
37+
"description": "The initial model prompt (i.e. the hidden instructions) to use when generating responses.",
38+
"default": "You are a helpful AI assistant. Please respond appropriately."
3739
},
3840
"page_title": {
3941
"type": "string",
4042
"title": "Page Title",
41-
"description": "The title to use for the chat interface."
43+
"description": "The title to use for the chat interface.",
44+
"default": "Large Language Model"
4245
},
4346
"llm_max_tokens": {
4447
"type": "number",
4548
"title": "Max Tokens",
46-
"description": "The maximum number of new [tokens](https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens) to generate for each LLM responses."
49+
"description": "The maximum number of new [tokens](https://platform.openai.com/docs/api-reference/chat/create#chat-create-max_tokens) to generate for each LLM responses.",
50+
"default": 1000
4751
},
4852
"llm_temperature": {
4953
"type": "number",
5054
"title": "LLM Temperature",
51-
"description": "The '[temperature](https://platform.openai.com/docs/api-reference/chat/create#chat-create-temperature)' value to use when generating LLM responses."
55+
"description": "The [temperature](https://platform.openai.com/docs/api-reference/chat/create#chat-create-temperature) value to use when generating LLM responses.",
56+
"default": 1
5257
},
5358
"llm_top_p": {
5459
"type": "number",
5560
"title": "LLM Top P",
56-
"description": "The [top p](https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_p) value to use when generating LLM responses."
61+
"description": "The [top p](https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_p) value to use when generating LLM responses.",
62+
"default": 1
5763
},
5864
"llm_presence_penalty": {
5965
"type": "number",
6066
"title": "LLM Presence Penalty",
61-
"description": "The [presence penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-presence_penalty) to use when generating LLM responses."
67+
"description": "The [presence penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-presence_penalty) to use when generating LLM responses.",
68+
"default": 0
6269
},
6370
"llm_frequency_penalty": {
6471
"type": "number",
6572
"title": "LLM Frequency Penalty",
66-
"description": "The [frequency_penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-frequency_penalty) to use when generating LLM responses."
73+
"description": "The [frequency_penalty](https://platform.openai.com/docs/api-reference/chat/create#chat-create-frequency_penalty) to use when generating LLM responses.",
74+
"default": 0
6775
}
6876

6977
},

0 commit comments

Comments
 (0)