Instructions to use liamka/sf-100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liamka/sf-100 with Transformers:

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

pipe = pipeline("text-generation", model="liamka/sf-100")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liamka/sf-100")
model = AutoModelForCausalLM.from_pretrained("liamka/sf-100", 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 liamka/sf-100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liamka/sf-100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liamka/sf-100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/liamka/sf-100

SGLang

How to use liamka/sf-100 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 "liamka/sf-100" \
    --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": "liamka/sf-100",
		"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 "liamka/sf-100" \
        --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": "liamka/sf-100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use liamka/sf-100 with Docker Model Runner:
```
docker model run hf.co/liamka/sf-100
```

sf-100

Conversational fine-tune of Qwen2.5-7B-Instruct, supervised-fine-tuned Hugging Face TRL.

Model details

Architecture: Qwen2 (7B)
Parameters: ~7.6B (reported as 8B in repo metadata)
Precision: BF16 merged weights, trained on top of a 4-bit bnb-quantized base
License: Apache-2.0
Language: Multi
Developed by: liamka

Intended use

General-purpose conversational assistant — single- and multi-turn chat.

Not suitable for safety-critical settings (medical, legal, financial advice), non-English input (not evaluated), or high-stakes factual lookup without verification.

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "liamka/sf-100"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [{"role": "user", "content": "Hi, who are you?"}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

out = model.generate(inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9)
print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

Training

Framework: Unsloth + TRL (SFTTrainer)
Method: Supervised fine-tuning on top of Qwen2.5-7B-Instruct
No RLHF / DPO applied

Dataset, step count and hyperparameters are not published.

Limitations

Inherits biases and knowledge cutoff from Qwen2.5-7B-Instruct.
SFT only — no preference optimisation, so safety and refusal behaviour matches the base or weaker.
Can hallucinate. Verify factual claims.
Evaluated only informally; no benchmark numbers reported.

Acknowledgements

Qwen2.5 — Alibaba
TRL — Hugging Face

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16