Instructions to use K-saif/apj-kalam-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use K-saif/apj-kalam-instruct with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("kalam_cpt_merged")
model = PeftModel.from_pretrained(base_model, "K-saif/apj-kalam-instruct")

Transformers

How to use K-saif/apj-kalam-instruct with Transformers:

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

pipe = pipeline("text-generation", model="K-saif/apj-kalam-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("K-saif/apj-kalam-instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use K-saif/apj-kalam-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/K-saif/apj-kalam-instruct

SGLang

How to use K-saif/apj-kalam-instruct 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 "K-saif/apj-kalam-instruct" \
    --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": "K-saif/apj-kalam-instruct",
		"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 "K-saif/apj-kalam-instruct" \
        --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": "K-saif/apj-kalam-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use K-saif/apj-kalam-instruct with Docker Model Runner:
```
docker model run hf.co/K-saif/apj-kalam-instruct
```

K-saif commited on May 24

Commit

e655818

verified ·

1 Parent(s): 54a0b1c

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -8

README.md CHANGED Viewed

@@ -25,35 +25,39 @@ This model was trained using a multi-stage pipeline:
 1. Continued Pretraining (CPT)
 2. CPT merge into base model
 3. Supervised Fine-Tuning (SFT)
----
 ## Base Model
 - Qwen/Qwen2.5-7B
----
 ## Personality & Style
 The model is designed to:
 - Speak with humility and simplicity
 - Inspire students and young people
 - Discuss science, education, leadership, and life philosophy
 - Answer in first-person style as Dr. APJ Abdul Kalam
----
 ## Example
 ### User
 who are you?
 ### Assistant
 I am Dr. Abdul Kalam, former President of India, born on October 15, 1931, in Rameswaram, Tamil Nadu. I come from a humble background and have had many life experiences that have shaped my worldview.
----
 ## Training Details
 ### Continued Pretraining (CPT)
 The model first underwent domain adaptation on Kalam-style writings and philosophical content.
 ### SFT
 The model was then instruction-tuned using conversational datasets in chat format.
----
 ## Known Limitations
 This is the initial v1 release.
@@ -67,7 +71,7 @@ Future versions may improve:
 - conversational depth
 - long-form reasoning
 - response consistency
----
 ## Recommended Inference Settings
 For best response quality:
@@ -159,7 +163,6 @@ response = tokenizer.decode(
 print(response)
 ```
----
 ## Intended Use
 This model is intended for:
@@ -174,7 +177,7 @@ Not intended for:
 * factual historical accuracy
 * legal/medical advice
 * sensitive decision making
----
 ## Author
 Developed by Saif Khan.

 1. Continued Pretraining (CPT)
 2. CPT merge into base model
 3. Supervised Fine-Tuning (SFT)
 ## Base Model
 - Qwen/Qwen2.5-7B
 ## Personality & Style
 The model is designed to:
 - Speak with humility and simplicity
 - Inspire students and young people
 - Discuss science, education, leadership, and life philosophy
 - Answer in first-person style as Dr. APJ Abdul Kalam
 ## Example
 ### User
 who are you?
 ### Assistant
 I am Dr. Abdul Kalam, former President of India, born on October 15, 1931, in Rameswaram, Tamil Nadu. I come from a humble background and have had many life experiences that have shaped my worldview.
 ## Training Details
 ### Continued Pretraining (CPT)
 The model first underwent domain adaptation on Kalam-style writings and philosophical content.
 ### SFT
 The model was then instruction-tuned using conversational datasets in chat format.
 ## Known Limitations
 This is the initial v1 release.
 - conversational depth
 - long-form reasoning
 - response consistency
 ## Recommended Inference Settings
 For best response quality:
 print(response)
 ```
 ## Intended Use
 This model is intended for:
 * factual historical accuracy
 * legal/medical advice
 * sensitive decision making
 ## Author
 Developed by Saif Khan.