Instructions to use ferrotorch/serialize-parity-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ferrotorch/serialize-parity-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ferrotorch/serialize-parity-v1",
	filename="gguf/SmolLM2-135M-Instruct-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ferrotorch/serialize-parity-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ferrotorch/serialize-parity-v1:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ferrotorch/serialize-parity-v1:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ferrotorch/serialize-parity-v1:Q8_0
# Run inference directly in the terminal:
llama-cli -hf ferrotorch/serialize-parity-v1:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ferrotorch/serialize-parity-v1:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ferrotorch/serialize-parity-v1:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ferrotorch/serialize-parity-v1:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ferrotorch/serialize-parity-v1:Q8_0

Use Docker

docker model run hf.co/ferrotorch/serialize-parity-v1:Q8_0

LM Studio
Jan
Ollama
How to use ferrotorch/serialize-parity-v1 with Ollama:
```
ollama run hf.co/ferrotorch/serialize-parity-v1:Q8_0
```

Unsloth Studio new

How to use ferrotorch/serialize-parity-v1 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 ferrotorch/serialize-parity-v1 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 ferrotorch/serialize-parity-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ferrotorch/serialize-parity-v1 to start chatting

Docker Model Runner
How to use ferrotorch/serialize-parity-v1 with Docker Model Runner:
```
docker model run hf.co/ferrotorch/serialize-parity-v1:Q8_0
```

Lemonade

How to use ferrotorch/serialize-parity-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ferrotorch/serialize-parity-v1:Q8_0

Run and chat with the model

lemonade run user.serialize-parity-v1-Q8_0

List all available models

lemonade list

`ferrotorch/serialize-parity-v1`

Phase G.3 of ferrotorch's real-artifact-driven development (#1169). Pins canonical references for ferrotorch-serialize's four format loaders/exporters so the rust crate's parsers and emitters can be verified byte-exact against the upstream toolchains they target.

Targets

.pth load — resnet18-pth/resnet18-5c106cde.pth is the official torchvision checkpoint (https://download.pytorch.org/models/resnet18-5c106cde.pth). reference_state_dict/<key>.bin carries each tensor as [u32 ndim][u32 shape...][f32 bytes]. The rust harness dumps the same per-tensor binaries via ferrotorch_serialize::load_pytorch_state_dict and compares byte-exact (max_abs = 0).
SafeTensors round-trip — safetensors-rt/resnet18.safetensors is the same resnet18 state_dict re-saved via safetensors.torch.save_file. References are the same per- tensor binaries as the .pth target. The rust harness compares byte-exact (max_abs = 0).
GGUF load — gguf/SmolLM-135M-Instruct-Q4_K_M.gguf is the upstream unsloth/SmolLM-135M-Instruct-GGUF checkpoint. reference_dequant/<name>.bin carries dequantized f32 tensors for a deterministic stride-sampled subset of layers, produced by python's gguf.GGUFReader. The rust harness reproduces those under max_abs <= 1e-4 (Q4_K group scaling has a known noise floor between implementations).
ONNX export — onnx-mlp/ carries:
- mlp_weights.bin — fixed-seed (torch.manual_seed(42)) weights for a Linear(4 -> 8) + ReLU + Linear(8 -> 2) MLP. The rust side reads these so its in-memory MLP matches torch's bit-for-bit before export.
- input_{zeros,ones,random}.bin — three fixed inputs.
- torch_forward_{zeros,ones,random}.bin — reference forward outputs from torch.nn.Sequential.
The rust harness builds the same MLP from mlp_weights.bin, exports it via ferrotorch_serialize::export_onnx, dumps the rust-side ferrotorch forward, and the python verifier loads the rust-emitted .onnx via onnxruntime.InferenceSession and asserts cosine_sim >= 0.9999 + max_abs <= 1e-5 across (rust-onnx vs rust-ferrotorch) AND (rust-onnx vs torch).

Provenance

Pin script: scripts/pin_pretrained_serialize_fixtures.py.
Verifier: scripts/verify_serialize_inference.py.
Rust dumps: ferrotorch-serialize/examples/serialize_{pth,safetensors,gguf,onnx_export}_dump.rs.
Cargo test wrapper: ferrotorch-serialize/tests/conformance_format_parity.rs.
Tracking issue: https://github.com/dollspace-gay/ferrotorch/issues/1169.
SHA-256 of bundle.tar (pinned in ferrotorch-hub/src/registry.rs): 7c20267db5706421e7367c4d275346114a43ff6d55e6ff1aa11069bc45562296.

Upstream licenses

resnet18 weights — BSD-3-Clause (torchvision).
SmolLM2-135M-Instruct-GGUF — Apache-2.0 (upstream unsloth mirror of HuggingFace's HuggingFaceTB/SmolLM2-135M-Instruct).
ferrotorch fixtures themselves — Apache-2.0 / MIT.

Downloads last month: 1

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support