Instructions to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Use Docker
docker model run hf.co/ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
- Ollama
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with Ollama:
ollama run hf.co/ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with Docker Model Runner:
docker model run hf.co/ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
- Lemonade
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.hishab-qwen3.5-0.8b-json-full-v8-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
hishab-qwen3.5-0.8b-json-full-v8-GGUF
Small on-device model for Hishab, a Bangladeshi personal-finance app. It reads a chat message in English, Bangla, Banglish (Bangla in Latin letters) or a mix, and returns the transactions in it as strict JSON:
user: Ajke tution fee 5k disi, riksha 80, cha 20
model: [{"description":"tuition fee","amount":5000.0,"category":"tuition","type":"expense"},{"description":"rickshaw","amount":80.0,"category":"transport","type":"expense"},{"description":"tea","amount":20.0,"category":"food","type":"expense"}]
Fields: description, amount (BDT), category (food, grocery, rent, utilities,
mobile_recharge, transport, tuition, salary, gift, loan, shopping, medical, entertainment,
other), type (income | expense). An empty array means no transaction.
This variant answers with the JSON array only.
Files
Evaluated with llama.cpp (greedy) on held-out splits of ryuma007/hishab-synthetic-v4: test (518 rows, all four
languages) and numbers (357 rows where every amount is spelled out in words, like "der hajar" or
"เฆชเฆจเงเฆฐเง เฆนเฆพเฆเฆพเฆฐ"). exact = the set of (amount, category, type) tuples equals the gold set.
| file | size | test exact | test tuple F1 | valid JSON | banglish exact | numbers exact |
|---|---|---|---|---|---|---|
qwen3.5-0.8b__json__full__v8-Q4_K_M-imat.gguf |
529 MB | 88.6 | 93.8 | 100.0 | 82.6 | 80.1 |
qwen3.5-0.8b__json__full__v8-Q5_K_M.gguf |
578 MB | 88.2 | 93.5 | 100.0 | 81.7 | 80.7 |
qwen3.5-0.8b__json__full__v8-Q6_K.gguf |
630 MB | 89.2 | 94.0 | 100.0 | 83.6 | 80.1 |
Training
Full fine-tune (all weights) of Qwen/Qwen3.5-0.8B, 3 epochs with TRL, lr 3e-05 cosine, completion-only loss, 20,333 training rows, best epoch
by validation loss. Importance
matrices (-imat files) were computed on rendered training conversations. Full pipeline and
all results: https://github.com/RaihanulHaque/hishab (ml/).
Use
llama-cli --hf-repo ryuma007/hishab-qwen3.5-0.8b-json-full-v8-GGUF --hf-file qwen3.5-0.8b__json__full__v8-Q4_K_M-imat.gguf --jinja \
-sys "You are Hishab, a Bangladeshi personal-finance assistant. The user writes in English, Bangla or Banglish (Bangla in Latin letters), often mixed. Extract every financial transaction they mention as a JSON array of objects with keys description, amount, category, type. Amounts are BDT numbers (expand shorthand like 1.5k or 2 lakh). category is one of: food, grocery, rent, utilities, mobile_recharge, transport, tuition, salary, gift, loan, shopping, medical, entertainment, other. type is income or expense. If there is no transaction, the array is empty. Reply with the JSON array only." \
-p "Salary paisi 35k but basha vara dilam 12k"
The system prompt above is the one used in training; keep it verbatim. Qwen3.5 models were
trained and must be run with thinking disabled (the default with --jinja). On Android the
model runs through kiln.
Trained on synthetic data only; expect lower accuracy on real messages until a human-labelled test set exists.
- Downloads last month
- 129
4-bit
5-bit
6-bit