Install from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf microtensor-archive/mt-code-3g-r1238-5CLfzJdv# Run inference directly in the terminal:
llama cli -hf microtensor-archive/mt-code-3g-r1238-5CLfzJdvBuild 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 microtensor-archive/mt-code-3g-r1238-5CLfzJdv# Run inference directly in the terminal:
./build/bin/llama cli -hf microtensor-archive/mt-code-3g-r1238-5CLfzJdvUse Docker
docker model run hf.co/microtensor-archive/mt-code-3g-r1238-5CLfzJdvMicrotensor archive 路 code/mt-3g 路 round 1238
This repository is an archival copy of a system submitted to the Microtensor subnet (Bittensor netuid 92) and certified by its validators. The figures below were measured by the network on reference hardware. They are not self-reported.
- Miner hotkey:
5CLfzJdvimUczt7WEUi7TqREzKCzLgSnarf93cYofFKyNaP2 - System digest:
82c9e2d2353dd3262368616c07b93277 - Arena: code / mt-3g
- Round: 1238
- Standing this round: confirmed
Measured record
- Quality: 0.5371
- Expected cost: 4230.0 ms per query
- Replication: 2
- Config hash:
sha256:221becaa24d6cb3d989dd7c790fa006e4a9de72d7c753894c7688fdc07b924c0 - Reports root:
sha256:25e76fe7c163deb54be513fa80060a03489956693f059c101613e33855c71107
The full signed record is in certificate.json. It is
recomputable from the round's published reports.
The artifact was fetched over a scheme that left no manifest file on disk; the bytes here are the component the network verified by digest and measured, retained without the submitted manifest.
Licence
Released under apache-2.0, the licence every base model allowed in this arena round carries (Qwen/Qwen2.5-Coder-0.5B-Instruct, Qwen/Qwen2.5-Coder-1.5B-Instruct, Qwen/Qwen3-0.6B, Qwen/Qwen3-1.7B).
Submitting granted the network the right to retain, archive and
redistribute this artifact, with emissions as the consideration.
Anyone may serve it, including commercially, on the terms of that licence.
- Downloads last month
- 32
We're not able to determine the quantization variants.
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf microtensor-archive/mt-code-3g-r1238-5CLfzJdv# Run inference directly in the terminal: llama cli -hf microtensor-archive/mt-code-3g-r1238-5CLfzJdv