Instructions to use nickmalhotra/ProjectIndus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nickmalhotra/ProjectIndus with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nickmalhotra/ProjectIndus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nickmalhotra/ProjectIndus")
model = AutoModelForCausalLM.from_pretrained("nickmalhotra/ProjectIndus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nickmalhotra/ProjectIndus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nickmalhotra/ProjectIndus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nickmalhotra/ProjectIndus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nickmalhotra/ProjectIndus

SGLang

How to use nickmalhotra/ProjectIndus with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nickmalhotra/ProjectIndus" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nickmalhotra/ProjectIndus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nickmalhotra/ProjectIndus" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nickmalhotra/ProjectIndus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nickmalhotra/ProjectIndus with Docker Model Runner:
```
docker model run hf.co/nickmalhotra/ProjectIndus
```

nickmalhotra commited on Apr 30, 2024

Commit

16da29a

1 Parent(s): 7596e2e

Update README.md

Browse files

Files changed (1) hide show

README.md +22 -9

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ model-index:
       value: 22.7
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nickmalhotra/indus_1.175B
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -108,7 +108,7 @@ model-index:
 # Model Card for Indus
 <!-- Provide a quick summary of what the model is/does. [Optional] -->
-The model is a single shot fine tuned Instruct LLM in Hindi and dialects
@@ -157,26 +157,32 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
 ## Model Description
 <!-- Provide a longer summary of what this model is/does. -->
-The model is a single shot fine tuned Instruct LLM in Hindi and dialects
 - **Developed by:** Nikhil Malhotra, Nilesh Brahme, Satish Mishra, Vinay Sharma (Makers Lab, TechMahindra)
 - **Model type:** Foundational Language model
 - **Language(s) (NLP):** hin, bho, mai, doi
 - **License:** other
-- **Parent Model:** It is the parent model on GPT architecture
-- **Resources for more information:** More information needed
 # Uses
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 ## Direct Use
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
@@ -184,7 +190,12 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
@@ -192,7 +203,7 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
 <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
@@ -203,12 +214,14 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
 Significant research has explored bias and fairness issues with language models
 (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
 Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
 ## Recommendations
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

       value: 22.7
       name: normalized accuracy
     source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nickmalhotra/ProjectIndus
       name: Open LLM Leaderboard
   - task:
       type: text-generation
 # Model Card for Indus
 <!-- Provide a quick summary of what the model is/does. [Optional] -->
+The model is a pretrained model in Hindi and dialects which is instruct tuned .
 ## Model Description
 <!-- Provide a longer summary of what this model is/does. -->
+TThe model is a pretrained model in Hindi and dialects which is instruct tuned.
 - **Developed by:** Nikhil Malhotra, Nilesh Brahme, Satish Mishra, Vinay Sharma (Makers Lab, TechMahindra)
 - **Model type:** Foundational Language model
 - **Language(s) (NLP):** hin, bho, mai, doi
 - **License:** other
+- **Parent Model:** It is a grounds up model built on GPT-2 architecture starting from tokenizer to decoder
+- **Resources for more information:** https://www.techmahindra.com/en-in/innovation/the-indus-project/
 # Uses
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+Uses include question and answeting and conversation in Hindi and Dialects. The model would be reward tuned to be used across various industries
+1. Call center
+2. Healthcare
+3. Automotive
+4. Telecom
 ## Direct Use
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
+Direct use is as a foundationla model on Hindi and dialects
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
+ Uses include question and answeting and conversation in Hindi and Dialects. The model would be reward tuned to be used across various industries
+1. Call center
+2. Healthcare
+3. Automotive
+4. Telecom
 <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
+Cannot be used for fill in the blanks, Multiple Q&A etc. at the moment
 Significant research has explored bias and fairness issues with language models
 (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
 Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
+We have taken care across various biases by trying to remove them from training data. However since the model is a generative model, it would tend to produce hallucinations.
+Any disturbing or harmful sterotype produced by the model is purely un-intentional and coincidental.
 ## Recommendations
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+Recommendation is to not use biases and negative connotation for the model