Instructions to use DJLougen/Qwen3.5-9B-Math-GraphCalc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DJLougen/Qwen3.5-9B-Math-GraphCalc with Transformers:

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

pipe = pipeline("text-generation", model="DJLougen/Qwen3.5-9B-Math-GraphCalc")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DJLougen/Qwen3.5-9B-Math-GraphCalc")
model = AutoModelForCausalLM.from_pretrained("DJLougen/Qwen3.5-9B-Math-GraphCalc", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DJLougen/Qwen3.5-9B-Math-GraphCalc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DJLougen/Qwen3.5-9B-Math-GraphCalc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DJLougen/Qwen3.5-9B-Math-GraphCalc",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DJLougen/Qwen3.5-9B-Math-GraphCalc

SGLang

How to use DJLougen/Qwen3.5-9B-Math-GraphCalc 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 "DJLougen/Qwen3.5-9B-Math-GraphCalc" \
    --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": "DJLougen/Qwen3.5-9B-Math-GraphCalc",
		"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 "DJLougen/Qwen3.5-9B-Math-GraphCalc" \
        --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": "DJLougen/Qwen3.5-9B-Math-GraphCalc",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DJLougen/Qwen3.5-9B-Math-GraphCalc with Docker Model Runner:
```
docker model run hf.co/DJLougen/Qwen3.5-9B-Math-GraphCalc
```

Qwen3.5-9B-Math-GraphCalc / firmware /build.sh

DJLougen

Upload Qwen3.5-9B-Math-GraphCalc (43-layer zero-gradient WSP + in-weights RV32 graphing calculator)

9b8659b verified 1 day ago

Raw History Blame Contribute Delete

1.58 kB

#!/bin/bash
# Build the Carbon Graphing Calculator RV32IM+Zba+Bignum firmware (run in WSL):
#   bash carbon/firmware/build.sh [OUT_DIR]
# Produces:
#   OUT_DIR/graphcalc.elf       (for compiled Qwen3.5 RV32 chip layers & chipformer.rv.ref.Machine)
#   OUT_DIR/graphcalc-qemu.elf  (for standalone qemu-riscv32 verification via stdin)
set -euo pipefail
HERE=$(cd "$(dirname "$0")" && pwd)
OUT=$(realpath "${1:-$HERE}")
QWENPUTER=${QWENPUTER:-$HERE/../../../qwenputer}
ENV=$QWENPUTER/experimental/riscv/chipformer/rv/env
CALC_ENV=$ENV/calc
GCC=riscv64-unknown-elf-gcc
MARCH=rv32im_zba
PICO=/usr/lib/picolibc/riscv64-unknown-elf
LIBC=$PICO/lib/release/rv32im/ilp32/libc.a
[ -f "$LIBC" ] || LIBC=$(find /usr/lib/picolibc -path '*rv32im/ilp32/libc.a' | head -n 1)
LIBGCC=$($GCC -march=rv32im -mabi=ilp32 -print-libgcc-file-name)

B=$(mktemp -d)
python3 "$HERE/tables.py" "$B/graphcalc_tables.h" "$B/sled.S"
mkdir -p "$OUT"

for map in rom qemu; do
  name=$([ $map = rom ] && echo graphcalc || echo graphcalc-qemu)
  def=$([ $map = rom ] && echo "" || echo "-DQEMU")
  sled=$([ $map = rom ] && echo "$B/sled.S" || echo "")
  $GCC -march=$MARCH -mabi=ilp32 ${CFLAGS:--O2} -fno-tree-loop-distribute-patterns -Wall -Wextra $def \
    -isystem "$PICO/include" -I"$ENV" -I"$CALC_ENV" -I"$B" \
    -nostdlib -nostartfiles -static -T"$ENV/$map.ld" -o "$OUT/$name.elf" \
    "$ENV/crt0.S" "$HERE/graphcalc.c" "$ENV/sys.c" $sled \
    -Wl,--start-group "$LIBC" "$LIBGCC" -Wl,--end-group
done

riscv64-unknown-elf-size -A "$OUT/graphcalc.elf" | grep -E '^\.(text|rodata|data|bss)'
rm -rf "$B"

	#!/bin/bash
	# Build the Carbon Graphing Calculator RV32IM+Zba+Bignum firmware (run in WSL):
	# bash carbon/firmware/build.sh [OUT_DIR]
	# Produces:
	# OUT_DIR/graphcalc.elf (for compiled Qwen3.5 RV32 chip layers & chipformer.rv.ref.Machine)
	# OUT_DIR/graphcalc-qemu.elf (for standalone qemu-riscv32 verification via stdin)
	set -euo pipefail
	HERE=$(cd "$(dirname "$0")" && pwd)
	OUT=$(realpath "${1:-$HERE}")
	QWENPUTER=${QWENPUTER:-$HERE/../../../qwenputer}
	ENV=$QWENPUTER/experimental/riscv/chipformer/rv/env
	CALC_ENV=$ENV/calc
	GCC=riscv64-unknown-elf-gcc
	MARCH=rv32im_zba
	PICO=/usr/lib/picolibc/riscv64-unknown-elf
	LIBC=$PICO/lib/release/rv32im/ilp32/libc.a
	[ -f "$LIBC" ] \|\| LIBC=$(find /usr/lib/picolibc -path '*rv32im/ilp32/libc.a' \| head -n 1)
	LIBGCC=$($GCC -march=rv32im -mabi=ilp32 -print-libgcc-file-name)

	B=$(mktemp -d)
	python3 "$HERE/tables.py" "$B/graphcalc_tables.h" "$B/sled.S"
	mkdir -p "$OUT"

	for map in rom qemu; do
	name=$([ $map = rom ] && echo graphcalc \|\| echo graphcalc-qemu)
	def=$([ $map = rom ] && echo "" \|\| echo "-DQEMU")
	sled=$([ $map = rom ] && echo "$B/sled.S" \|\| echo "")
	$GCC -march=$MARCH -mabi=ilp32 ${CFLAGS:--O2} -fno-tree-loop-distribute-patterns -Wall -Wextra $def \
	-isystem "$PICO/include" -I"$ENV" -I"$CALC_ENV" -I"$B" \
	-nostdlib -nostartfiles -static -T"$ENV/$map.ld" -o "$OUT/$name.elf" \
	"$ENV/crt0.S" "$HERE/graphcalc.c" "$ENV/sys.c" $sled \
	-Wl,--start-group "$LIBC" "$LIBGCC" -Wl,--end-group
	done

	riscv64-unknown-elf-size -A "$OUT/graphcalc.elf" \| grep -E '^\.(text\|rodata\|data\|bss)'
	rm -rf "$B"