Instructions to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct")
model = AutoModelForCausalLM.from_pretrained("nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct", 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 nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nassimjp/MiniCPM5-2B-SFT-Pashto-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": "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct

SGLang

How to use nassimjp/MiniCPM5-2B-SFT-Pashto-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 "nassimjp/MiniCPM5-2B-SFT-Pashto-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": "nassimjp/MiniCPM5-2B-SFT-Pashto-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 "nassimjp/MiniCPM5-2B-SFT-Pashto-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": "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct with Docker Model Runner:
```
docker model run hf.co/nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MiniCPM5-2B-SFT-Pashto-Instruct 🚀🧬🇦🇫

MiniCPM5-2B-SFT-Pashto-Instruct is a specialized Pashto instruction-tuned model developed as part of the iPashto.ai initiative. The model is fine-tuned from the openbmb/MiniCPM-2B-sft-bf16 backbone using LoRA/QLoRA adapter techniques and fully merged into 16-bit (bfloat16) safetensors format for native deployment and further downstream tuning.

Model Details

Developed by: Nassimjp / iPashto.ai
Base Model: openbmb/MiniCPM-2B-sft-bf16
Language: Pashto (ps)
License: Apache-2.0
Architecture: Causal LM (MiniCPM Architecture)
Precision: 16-bit (bfloat16 Merged)
Training Method: Supervised Fine-Tuning (SFT) via LoRA

Training Highlights & Loss Metrics

The fine-tuning run was executed locally using an NVIDIA RTX 4070 Ti SUPER (16GB VRAM) across 8,952 steps.

Training Loss: Reduced smoothly from 4.61 to ~0.54
Evaluation Loss: Consistent descent down to ~0.91 without overfitting
Gradient Norm: Maintained stable updates around 1.4 - 2.2

Quickstart & Usage

1. Using Transformers (Python)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

prompt = "د پښتو ژبې او مصنوعي ځیرکتیا پرمختګ څه اهمیت لري؟"

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

2. Running via llama.cpp / GGUF

For edge deployment or GGUF quantization, load the merged weights into llama.cpp:

./llama-cli -m ./MiniCPM5-2B-SFT-Pashto-Instruct.F16.gguf \
  -p "پښتو ژبه د افغانستان..." \
  -n 256

Project Context

Developed under the iPashto.ai framework dedicated to advancing Pashto Natural Language Processing (NLP), specialized datasets, and open-weight AI accessibility for low-resource languages.

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct

Base model

openbmb/MiniCPM-2B-sft-bf16

Adapter

(1)

this model

Quantizations

1 model