Instructions to use ahmadhehe/tinyllama-1.1b-sft-dolly15k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ahmadhehe/tinyllama-1.1b-sft-dolly15k with Transformers:

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

pipe = pipeline("text-generation", model="ahmadhehe/tinyllama-1.1b-sft-dolly15k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ahmadhehe/tinyllama-1.1b-sft-dolly15k")
model = AutoModelForCausalLM.from_pretrained("ahmadhehe/tinyllama-1.1b-sft-dolly15k")
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 Settings

vLLM

How to use ahmadhehe/tinyllama-1.1b-sft-dolly15k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ahmadhehe/tinyllama-1.1b-sft-dolly15k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahmadhehe/tinyllama-1.1b-sft-dolly15k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ahmadhehe/tinyllama-1.1b-sft-dolly15k

SGLang

How to use ahmadhehe/tinyllama-1.1b-sft-dolly15k 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 "ahmadhehe/tinyllama-1.1b-sft-dolly15k" \
    --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": "ahmadhehe/tinyllama-1.1b-sft-dolly15k",
		"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 "ahmadhehe/tinyllama-1.1b-sft-dolly15k" \
        --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": "ahmadhehe/tinyllama-1.1b-sft-dolly15k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ahmadhehe/tinyllama-1.1b-sft-dolly15k with Docker Model Runner:
```
docker model run hf.co/ahmadhehe/tinyllama-1.1b-sft-dolly15k
```

Best SFT Model — SFT-T4

TinyLlama-1.1B-Chat-v1.0 fine-tuned via Supervised Fine-Tuning (SFT) on databricks/databricks-dolly-15k.

Authors

Ahmad Murtaza (24478)
Simra Sheikh (27135)

Project Context

This model was developed as part of Assignment 04 for the NLP with Deep Learning course at the Institute of Business Administration (IBA). The assignment involves building a full SFT → DPO fine-tuning pipeline on TinyLlama-1.1B-Chat-v1.0 and evaluating the impact of instruction tuning and preference alignment.

Training config

trial         : SFT-T4
lora_rank     : 16
lora_alpha    : 32
target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']
learning_rate : 0.0002
epochs        : 1
val_loss      : 1.7798

Evaluation (10-prompt test set, merged model)

Model	BLEU-4	BERTScore F1
Base (TinyLlama-1.1B)	2.1400	85.4700
Best SFT (SFT-T4)	2.4200	87.1100

Downloads last month: 6

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for ahmadhehe/tinyllama-1.1b-sft-dolly15k

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Adapter

(1549)

this model