whatmodel.sh / Code-290k-6.7B-Instruct

Code-290k-6.7B-Instruct

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Code-290k-6.7B-Instruct is an open-weights language model from ajibawa-2023, released February 2024. Its published size is 6.74B parameters. Licence: other.

Catalogue identity notes

Maker repo ajibawa-2023/Code-290k-6.7B-Instruct @e4a8296: licence tag other. 6,740,512,768 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-02: month the maker's Hugging Face repo was created (createdAt 2024-02-25).

44.4±0.8#598 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Code-290k-6.7B-Instruct, out of 1132 with a score, then more from ajibawa-2023.

#modelscorewhereRAMreleased
751Jais Adapted 70B Chat Inception (G42)45±4local~293GB2024-08
752Mistral NeMo Instruct (2407) Mistral44±1local~8.7GB2024-07
753Code-290k-6.7B-Instruct ajibawa-202344±1local~5.8GB2024-02
754FuseChat-Llama-3.2-1B-Instruct FuseAI44±2local~2.3GB2024-11
755LLaVA-OneVision Qwen2 72B (ov-sft) LLaVA (lmms-lab)44±3local~155GB2024-08
more from ajibawa-2023
836Code-13B (ajibawa-2023) ajibawa-202342±1local~9.8GB2023-12
852Code-33B (ajibawa-2023) ajibawa-202341±1local~22GB2023-12
866OpenHermes-2.5-Code-290k-13B ajibawa-202341±1local~9.8GB2024-03

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #337 of 469 * · 100% of its score · 2 tests

Beats GLM-4.7-Flash, LFM2.5 2.6B, LFM2.5 8B-A1B here, though they rank higher overall. Trails Phi-3-mini-128k-instruct (Apr 2024), DeepSeek LLM 67B Chat, WizardLM 70B V1.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
HumanEval64.6% ✎▁·▁▁▃▄▆▅█▃▁▁ beats 50/99easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 56%sharp · at its level
HumanEval+59.7% ✎▁·▁▁▁▃▄▄▄█▃▁ beats 51/99easy · avg 74%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 43%sharp · at its level

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Code-290k-6.7B-Instruct · needs ~4.1 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Code-290k-6.7B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Code-290k-6.7B-Instruct-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Code-290k-6.7B-Instruct · needs ~4.1 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Code-290k-6.7B-Instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Code-290k-6.7B-Instruct · needs ~4.1 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Code-290k-6.7B-Instruct-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~13.48 GB · from huggingface.co/ajibawa-2023 (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='ajibawa-2023/Code-290k-6.7B-Instruct', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/ajibawa-2023 ↗

$ how the score was worked out · EvalPlus / EvalPerf published… 100%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
EvalPlus / EvalPerf published evaluation runs2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%Apache-2.0
prior · pull toward the middle▇ 0%
weighted average= 44.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json