Instructions to use Pinkstackorg/Fijik1-3b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstackorg/Fijik1-3b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstackorg/Fijik1-3b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstackorg/Fijik1-3b-instruct")
model = AutoModelForCausalLM.from_pretrained("Pinkstackorg/Fijik1-3b-instruct")
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 Pinkstackorg/Fijik1-3b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstackorg/Fijik1-3b-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": "Pinkstackorg/Fijik1-3b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstackorg/Fijik1-3b-instruct

SGLang

How to use Pinkstackorg/Fijik1-3b-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 "Pinkstackorg/Fijik1-3b-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": "Pinkstackorg/Fijik1-3b-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 "Pinkstackorg/Fijik1-3b-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": "Pinkstackorg/Fijik1-3b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use Pinkstackorg/Fijik1-3b-instruct with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pinkstackorg/Fijik1-3b-instruct to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pinkstackorg/Fijik1-3b-instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Pinkstackorg/Fijik1-3b-instruct to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Pinkstackorg/Fijik1-3b-instruct",
    max_seq_length=2048,
)

Docker Model Runner
How to use Pinkstackorg/Fijik1-3b-instruct with Docker Model Runner:
```
docker model run hf.co/Pinkstackorg/Fijik1-3b-instruct
```

Pinkstack commited on May 25, 2025

Commit

8d5d394

verified ·

1 Parent(s): ffaaad9

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -1

README.md CHANGED Viewed

@@ -42,7 +42,22 @@ Fijik 1.0 3B is by design, meant to be a production-ready, general use, high-per
 - Coding, Math: In our SFT, DPO fine-tuning data we have put an effort into improving coding and step-by-step math performance, while it is indeed not perfect, no LLM is.
 # Examples
-none yet
 # Limitations
 This model is not uncensored, yet it may produce erotic outputs. You are solely responsible for the outputs from the model.

 - Coding, Math: In our SFT, DPO fine-tuning data we have put an effort into improving coding and step-by-step math performance, while it is indeed not perfect, no LLM is.
 # Examples
+```What is 8.8-8.11?``` (surprisingly a specific new SOTA llm got this wrong but our model didn't.)
+<details>
+  <summary style="background-color: #007bff; color: white; padding: 12px 24px; text-align: center; display: inline-block; font-size: 16px; margin: 4px 2px; cursor: pointer; border-radius: 8px; user-select: none; list-style: none;">Send</summary>
+  <div style="margin-top: 10px; padding: 15px; border: 1px solid #ddd; border-radius: 8px; background-color: #f9f9f9; color: black; font-family: monospace;">
+To find the result of 8.8-8.11, we simply perform the subtraction:
+8.8 - 8.11 = 0.69
+So, 8.8-8.11 equals 0.69.
+  </div>
+</details>
+<style>
+  details > summary::-webkit-details-marker {
+    display: none;
+  }
+</style>
 # Limitations
 This model is not uncensored, yet it may produce erotic outputs. You are solely responsible for the outputs from the model.