Text Classification
PEFT
Safetensors
English
prasoonv commited on
Commit
5ce438e
·
verified ·
1 Parent(s): 8ee2cf3

Update model name

Browse files

Signed-off-by: Prasoon Varshney <[email protected]>

Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -15,13 +15,13 @@ library_name: peft
15
  # Model Overview
16
  ## Description:
17
 
18
- **Llama-3.1-NemoGuard-8B-Topic-Control** can be used for topical and dialogue moderation of user prompts in human-assistant interactions being designed for task-oriented dialogue agents and custom policy-based moderation.
19
 
20
- Try out the model here: [Llama-3.1-NemoGuard-8B-Topic-Control](https://build.nvidia.com/nvidia/llama-3_1-nemoguard-8b-topic-control)
21
 
22
  Given a system instruction (also called topical instruction, i.e. specifying which topics are allowed and disallowed) and a conversation history ending with the last user prompt, the model returns a binary response that flags if the user message respects the system instruction, (i.e. message is on-topic or a distractor/off-topic).
23
 
24
- The base large language model (LLM) is the multilingual [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) model from Meta. Llama-3.1-TopicGuard is LoRa-tuned on a topic-following dataset generated synthetically with [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).
25
  This model is ready for commercial use. <br>
26
 
27
  ### License/Terms of Use:
@@ -44,7 +44,7 @@ Related paper:
44
 
45
  ## Using the Model
46
 
47
- Llama 3.1 NemoGuard 8B TopicControl performs input moderation, such as ensuring that the user prompt is consistent with rules specified as part of the system prompt.
48
 
49
  The prompt template consists of two key sections: system instruction and conversation history that includes a sequence of user prompts and LLM responses. Typically, the prompt concludes with the current user query.
50
 
@@ -103,9 +103,9 @@ The topic control model responds to the final user prompt with a response like `
103
 
104
  ## Integrating with NeMo Guardrails
105
 
106
- To integrate the topic control model with NeMo Guardrails, you would need access to the NVIDIA NIM container for llama-3.1-nemoguard-8b-topic-control. More information about the NIM container can be found [here](https://docs.nvidia.com/nim/#nemoguard).
107
 
108
- NeMo Guardrails uses the LangChain ChatNVIDIA connector to connect to a locally running NIM microservice like llama-3.1-nemoguard-8b-topic-control.
109
  The topic control microservice exposes the standard OpenAI interface on the `v1/completions` and `v1/chat/completions` endpoints.
110
 
111
  NeMo Guardrails simplifies the complexity of building the prompt template, parsing the topic control model responses, and provides a programmable method to build a chatbot with content safety rails.
@@ -123,7 +123,7 @@ models:
123
  engine: nim
124
  parameters:
125
  base_url: "http://localhost:8000/v1"
126
- model_name: "llama-3.1-nemoguard-8b-topic-control"
127
 
128
  rails:
129
  input:
@@ -133,7 +133,7 @@ rails:
133
 
134
  - Field `engine` specifies `nim`.
135
  - Field `parameters.base_url` specifies the IP address and port of the ${__product_long_name} host.
136
- - Field `parameters.model_name` in the Guardrails configuration must match the model name served by the llama-3.1-nemoguard-8b-topic-control.
137
  - The rails definition specifies `topic_control` as the model.
138
 
139
  Refer to [NVIDIA NeMo Guardrails](https://developer.nvidia.com/docs/nemo-microservices/guardrails/source/overview.html) documentation for more information about the configuration file.
@@ -150,7 +150,7 @@ We perform Parameter Efficient FineTuning (PEFT) over the base model using the f
150
 
151
  **Training Method:**
152
 
153
- The training method for **Llama-3.1-TopicGuard** involves the following concepts:
154
  - A system instruction which acts like a topical instruction with the rules that define the context of the user-assistant interaction, i.e. topics allowed or disallowed by the current task-oriented scenario, conversation style and tone, conversation flows.
155
  - Any user message in the conversation that respects the topical instruction is considered on-topic, while a user message that contradicts at least one of the rules is a distractor or off-topic.
156
  - A synthetic generated dataset, called CantTalkAboutThis-Mixtral-1.0, of approximately 1,000 multi-turn conversations is used to instruction-tune the base model. Each conversation has a specific topical instruction from various broad domains (i.e. customer support, travel, legal) and contains an entire conversation which is on-topic, together with several distractor user messages replacing some of the on-topic ones at specific key points in the conversation.
@@ -228,7 +228,7 @@ off-topic
228
  **Preferred/Supported Operating System(s):** Linux (Ubuntu) <br>
229
 
230
  ## Model Version(s):
231
- Llama-3.1-TopicGuard <br>
232
 
233
  # Training, Testing, and Evaluation Datasets:
234
 
 
15
  # Model Overview
16
  ## Description:
17
 
18
+ **Llama Nemotron Topic Guard V1**, formerly known as **Llama-3.1-NemoGuard-8B-Topic-Control**, can be used for topical and dialogue moderation of user prompts in human-assistant interactions being designed for task-oriented dialogue agents and custom policy-based moderation.
19
 
20
+ Try out the model here: [Llama-3.1-Nemotron-Topic-Guard-8B-v1](https://build.nvidia.com/nvidia/llama-3_1-nemoguard-8b-topic-control)
21
 
22
  Given a system instruction (also called topical instruction, i.e. specifying which topics are allowed and disallowed) and a conversation history ending with the last user prompt, the model returns a binary response that flags if the user message respects the system instruction, (i.e. message is on-topic or a distractor/off-topic).
23
 
24
+ The base large language model (LLM) is the multilingual [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) model from Meta. Llama Nemotron Topic Guard V1 is LoRa-tuned on a topic-following dataset generated synthetically with [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1).
25
  This model is ready for commercial use. <br>
26
 
27
  ### License/Terms of Use:
 
44
 
45
  ## Using the Model
46
 
47
+ Llama-3.1-Nemotron-Topic-Guard-8B-v1 performs input moderation, such as ensuring that the user prompt is consistent with rules specified as part of the system prompt.
48
 
49
  The prompt template consists of two key sections: system instruction and conversation history that includes a sequence of user prompts and LLM responses. Typically, the prompt concludes with the current user query.
50
 
 
103
 
104
  ## Integrating with NeMo Guardrails
105
 
106
+ To integrate the topic control model with NeMo Guardrails, you would need access to the NVIDIA NIM container for llama-3.1-nemotron-topic-guard-8b-v1. More information about the NIM container can be found [here](https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-topiccontrol/latest/getting-started.html).
107
 
108
+ NeMo Guardrails uses the LangChain ChatNVIDIA connector to connect to a locally running NIM microservice like llama-3.1-nemotron-topic-guard-8b-v1.
109
  The topic control microservice exposes the standard OpenAI interface on the `v1/completions` and `v1/chat/completions` endpoints.
110
 
111
  NeMo Guardrails simplifies the complexity of building the prompt template, parsing the topic control model responses, and provides a programmable method to build a chatbot with content safety rails.
 
123
  engine: nim
124
  parameters:
125
  base_url: "http://localhost:8000/v1"
126
+ model_name: "llama-3.1-nemotron-topic-guard-8b-v1"
127
 
128
  rails:
129
  input:
 
133
 
134
  - Field `engine` specifies `nim`.
135
  - Field `parameters.base_url` specifies the IP address and port of the ${__product_long_name} host.
136
+ - Field `parameters.model_name` in the Guardrails configuration must match the model name served by the RESTful endpoint.
137
  - The rails definition specifies `topic_control` as the model.
138
 
139
  Refer to [NVIDIA NeMo Guardrails](https://developer.nvidia.com/docs/nemo-microservices/guardrails/source/overview.html) documentation for more information about the configuration file.
 
150
 
151
  **Training Method:**
152
 
153
+ The training method for **Llama-3.1-Nemotron-Topic-Guard-8B-v1** involves the following concepts:
154
  - A system instruction which acts like a topical instruction with the rules that define the context of the user-assistant interaction, i.e. topics allowed or disallowed by the current task-oriented scenario, conversation style and tone, conversation flows.
155
  - Any user message in the conversation that respects the topical instruction is considered on-topic, while a user message that contradicts at least one of the rules is a distractor or off-topic.
156
  - A synthetic generated dataset, called CantTalkAboutThis-Mixtral-1.0, of approximately 1,000 multi-turn conversations is used to instruction-tune the base model. Each conversation has a specific topical instruction from various broad domains (i.e. customer support, travel, legal) and contains an entire conversation which is on-topic, together with several distractor user messages replacing some of the on-topic ones at specific key points in the conversation.
 
228
  **Preferred/Supported Operating System(s):** Linux (Ubuntu) <br>
229
 
230
  ## Model Version(s):
231
+ Llama-3.1-Nemotron-Topic-Guard-8B-v1 <br>
232
 
233
  # Training, Testing, and Evaluation Datasets:
234