Instructions to use venkateshchsagalm/SagaLM-slm2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use venkateshchsagalm/SagaLM-slm2 with Transformers:

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

pipe = pipeline("text-generation", model="venkateshchsagalm/SagaLM-slm2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("venkateshchsagalm/SagaLM-slm2")
model = AutoModelForCausalLM.from_pretrained("venkateshchsagalm/SagaLM-slm2", device_map="auto")
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 venkateshchsagalm/SagaLM-slm2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "venkateshchsagalm/SagaLM-slm2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "venkateshchsagalm/SagaLM-slm2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/venkateshchsagalm/SagaLM-slm2

SGLang

How to use venkateshchsagalm/SagaLM-slm2 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 "venkateshchsagalm/SagaLM-slm2" \
    --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": "venkateshchsagalm/SagaLM-slm2",
		"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 "venkateshchsagalm/SagaLM-slm2" \
        --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": "venkateshchsagalm/SagaLM-slm2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use venkateshchsagalm/SagaLM-slm2 with Docker Model Runner:
```
docker model run hf.co/venkateshchsagalm/SagaLM-slm2
```

SagaLM-slm2

SagaLM is a QLoRA/SFT fine-tuned Large Language Model derived from Qwen/Qwen2.5-7B-Instruct.

Important

The underlying architecture remains compatible with the Qwen2/Qwen2.5 Transformers implementation. SagaLM is the model and assistant identity; the internal model_type is intentionally not renamed to ensure compatibility with the Transformers ecosystem.

Training

Base model: Qwen/Qwen2.5-7B-Instruct
Context length: 2,048 tokens
Fine-tuning method: QLoRA / Supervised Fine-Tuning (SFT)
LoRA rank: 16
LoRA alpha: 32
LoRA dropout: 0.05
Effective batch size: 4
Training steps: 1,200
Completion-only loss (prompt tokens masked to -100)
Long-answer token filtering with short identity-grounding examples
Training mixture includes instruction following, conversations, reasoning, mathematics, and coding datasets

Identity

SagaLM is trained to identify itself as SagaLM rather than Qwen, ChatGPT, Claude, or another named assistant.

Generation Recommendation

max_new_tokens: 1024
temperature: 0.7
top_p: 0.9
top_k: 50
repetition_penalty: 1.05

Downloads last month: 651

Safetensors

Model size

8B params

Tensor type

F16

Model tree for venkateshchsagalm/SagaLM-slm2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3041)

this model