Instructions to use jstarks/Qwen3.5-4B-Weight-Space-Programming with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Transformers:

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

pipe = pipeline("text-generation", model="jstarks/Qwen3.5-4B-Weight-Space-Programming")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jstarks/Qwen3.5-4B-Weight-Space-Programming")
model = AutoModelForMultimodalLM.from_pretrained("jstarks/Qwen3.5-4B-Weight-Space-Programming", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming 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 jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming: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 jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Use Docker

docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jstarks/Qwen3.5-4B-Weight-Space-Programming"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

SGLang

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming 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 "jstarks/Qwen3.5-4B-Weight-Space-Programming" \
    --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": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"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 "jstarks/Qwen3.5-4B-Weight-Space-Programming" \
        --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": "jstarks/Qwen3.5-4B-Weight-Space-Programming",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Ollama:
```
ollama run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
```
Unsloth Desktop

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming: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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Docker Model Runner:
```
docker model run hf.co/jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M
```

Lemonade

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-Weight-Space-Programming-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming: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://127.0.0.1:8080/v1
hermes config set model.default jstarks/Qwen3.5-4B-Weight-Space-Programming:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jstarks/Qwen3.5-4B-Weight-Space-Programming with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jstarks/Qwen3.5-4B-Weight-Space-Programming: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://127.0.0.1:8080/v1 \
  --custom-model-id "jstarks/Qwen3.5-4B-Weight-Space-Programming: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"

Qwen3.5-4B-Weight-Space-Programming / scripts /apply_patch.py

jstarks

Upload Q4_K_M GGUF, full BF16 HF checkpoint, safetensors patches (r16 + dense delta), and apply_patch.py

8018ecd verified 1 day ago

Raw History Blame Contribute Delete

3.49 kB

"""Apply Qwen/Qwen3.5-4B WSP v2.5 safetensors patches (factored r16 subspaces or dense delta)
to a loaded Hugging Face Qwen3.5-4B model in-memory.
Supports Variant 3 regime presets cleanly:
  - general_fast_think : scales=[1.95, 0.0, 0.0, 0.0, 0.0, 0.0]
  - mid_code_synthesis : scales=[0.65, 0.0, 0.0, 0.65, 0.0, 0.0]
  - tool_routing       : scales=[0.70, 0.0, 0.95, 0.0, 0.0, 0.0]
  - turn2_json         : scales=[0.70, 0.40, 0.0, 0.0, 1.0, 0.0]
  - restraint_pushback : scales=[0.70, 1.0, 0.0, 0.0, 0.0, 0.0]
  - escalate_handoff   : scales=[0.70, 0.0, 0.0, 0.0, 0.0, 1.0]
"""

from __future__ import annotations

import json
from pathlib import Path
from typing import Dict, List, Sequence
import torch
from safetensors.torch import load_file

SUBSPACE_PATCH_FILES = [
    "wsp_s1_think_r16.safetensors",
    "wsp_s2_restraint_r16.safetensors",
    "wsp_s3_router_r16.safetensors",
    "wsp_s4_mid_code_r16.safetensors",
    "wsp_s5_json_schema_r16.safetensors",
    "wsp_s6_handoff_r16.safetensors",
]

REGIME_PRESETS: Dict[str, List[float]] = {
    "general_fast_think": [1.95, 0.0, 0.0, 0.0, 0.0, 0.0],
    "mid_code_synthesis": [0.65, 0.0, 0.0, 0.65, 0.0, 0.0],
    "tool_routing": [0.70, 0.0, 0.95, 0.0, 0.0, 0.0],
    "turn2_json_synthesis": [0.70, 0.40, 0.0, 0.0, 1.0, 0.0],
    "restraint_pushback": [0.70, 1.0, 0.0, 0.0, 0.0, 0.0],
    "handoff_gate": [0.70, 0.0, 0.0, 0.0, 0.0, 1.0],
    "static_all_on_v2": [0.65, 0.65, 0.65, 0.65, 0.65, 0.65],
}


def apply_subspace_scales_to_hf_model(
    model: torch.nn.Module,
    patches_dir: Path | str,
    scales: Sequence[float],
    use_s4_oproj: bool = False,
) -> int:
    """Add sum_i scale[i] * (lora_b @ lora_a) directly into HF model weights in-place."""
    if len(scales) != 6:
        raise ValueError(f"Expected 6 subspace scales, got {len(scales)}")
    pdir = Path(patches_dir)
    params = dict(model.named_parameters())
    updated_tensors = 0

    with torch.no_grad():
        for i, fname in enumerate(SUBSPACE_PATCH_FILES):
            sc = float(scales[i])
            if abs(sc) < 1e-9:
                continue
            target_file = pdir / ("wsp_s4_mid_code_oproj_r16.safetensors" if (i == 3 and use_s4_oproj) else fname)
            tensors = load_file(str(target_file), device="cpu")
            prefixes = sorted({k[:-7] for k in tensors if k.endswith(".lora_a")})
            for hf_key in prefixes:
                param = params[hf_key]
                la = tensors[f"{hf_key}.lora_a"].to(device=param.device, dtype=torch.float32)
                lb = tensors[f"{hf_key}.lora_b"].to(device=param.device, dtype=torch.float32)
                delta = sc * (lb @ la)
                param.add_(delta.to(dtype=param.dtype))
                updated_tensors += 1
    return updated_tensors


def apply_dense_patch_to_hf_model(
    model: torch.nn.Module,
    dense_patch_path: Path | str,
    scale: float = 1.0,
) -> int:
    """Add scale * delta tensors from wsp_qwen35_4b_patch.safetensors directly in-place."""
    tensors = load_file(str(dense_patch_path), device="cpu")
    params = dict(model.named_parameters())
    updated = 0
    with torch.no_grad():
        for key, delta in tensors.items():
            if not key.endswith(".delta"):
                continue
            hf_key = key[: -len(".delta")]
            param = params[hf_key]
            param.add_((scale * delta.to(device=param.device, dtype=torch.float32)).to(dtype=param.dtype))
            updated += 1
    return updated

	"""Apply Qwen/Qwen3.5-4B WSP v2.5 safetensors patches (factored r16 subspaces or dense delta)
	to a loaded Hugging Face Qwen3.5-4B model in-memory.

	Supports Variant 3 regime presets cleanly:
	- general_fast_think : scales=[1.95, 0.0, 0.0, 0.0, 0.0, 0.0]
	- mid_code_synthesis : scales=[0.65, 0.0, 0.0, 0.65, 0.0, 0.0]
	- tool_routing : scales=[0.70, 0.0, 0.95, 0.0, 0.0, 0.0]
	- turn2_json : scales=[0.70, 0.40, 0.0, 0.0, 1.0, 0.0]
	- restraint_pushback : scales=[0.70, 1.0, 0.0, 0.0, 0.0, 0.0]
	- escalate_handoff : scales=[0.70, 0.0, 0.0, 0.0, 0.0, 1.0]
	"""

	from __future__ import annotations

	import json
	from pathlib import Path
	from typing import Dict, List, Sequence
	import torch
	from safetensors.torch import load_file

	SUBSPACE_PATCH_FILES = [
	"wsp_s1_think_r16.safetensors",
	"wsp_s2_restraint_r16.safetensors",
	"wsp_s3_router_r16.safetensors",
	"wsp_s4_mid_code_r16.safetensors",
	"wsp_s5_json_schema_r16.safetensors",
	"wsp_s6_handoff_r16.safetensors",
	]

	REGIME_PRESETS: Dict[str, List[float]] = {
	"general_fast_think": [1.95, 0.0, 0.0, 0.0, 0.0, 0.0],
	"mid_code_synthesis": [0.65, 0.0, 0.0, 0.65, 0.0, 0.0],
	"tool_routing": [0.70, 0.0, 0.95, 0.0, 0.0, 0.0],
	"turn2_json_synthesis": [0.70, 0.40, 0.0, 0.0, 1.0, 0.0],
	"restraint_pushback": [0.70, 1.0, 0.0, 0.0, 0.0, 0.0],
	"handoff_gate": [0.70, 0.0, 0.0, 0.0, 0.0, 1.0],
	"static_all_on_v2": [0.65, 0.65, 0.65, 0.65, 0.65, 0.65],
	}


	def apply_subspace_scales_to_hf_model(
	model: torch.nn.Module,
	patches_dir: Path \| str,
	scales: Sequence[float],
	use_s4_oproj: bool = False,
	) -> int:
	"""Add sum_i scale[i] * (lora_b @ lora_a) directly into HF model weights in-place."""
	if len(scales) != 6:
	raise ValueError(f"Expected 6 subspace scales, got {len(scales)}")
	pdir = Path(patches_dir)
	params = dict(model.named_parameters())
	updated_tensors = 0

	with torch.no_grad():
	for i, fname in enumerate(SUBSPACE_PATCH_FILES):
	sc = float(scales[i])
	if abs(sc) < 1e-9:
	continue
	target_file = pdir / ("wsp_s4_mid_code_oproj_r16.safetensors" if (i == 3 and use_s4_oproj) else fname)
	tensors = load_file(str(target_file), device="cpu")
	prefixes = sorted({k[:-7] for k in tensors if k.endswith(".lora_a")})
	for hf_key in prefixes:
	param = params[hf_key]
	la = tensors[f"{hf_key}.lora_a"].to(device=param.device, dtype=torch.float32)
	lb = tensors[f"{hf_key}.lora_b"].to(device=param.device, dtype=torch.float32)
	delta = sc * (lb @ la)
	param.add_(delta.to(dtype=param.dtype))
	updated_tensors += 1
	return updated_tensors


	def apply_dense_patch_to_hf_model(
	model: torch.nn.Module,
	dense_patch_path: Path \| str,
	scale: float = 1.0,
	) -> int:
	"""Add scale * delta tensors from wsp_qwen35_4b_patch.safetensors directly in-place."""
	tensors = load_file(str(dense_patch_path), device="cpu")
	params = dict(model.named_parameters())
	updated = 0
	with torch.no_grad():
	for key, delta in tensors.items():
	if not key.endswith(".delta"):
	continue
	hf_key = key[: -len(".delta")]
	param = params[hf_key]
	param.add_((scale * delta.to(device=param.device, dtype=torch.float32)).to(dtype=param.dtype))
	updated += 1
	return updated