MexIvanov/ zephyr-python-ru:Q8_0

14 1 year ago

An experimental finetune of Zephyr-7b-beta, aimed at improving coding performance and support for coding-related instructions written in Russian language. 

ollama run MexIvanov/zephyr-python-ru:Q8_0

Details

1 year ago

f5030076768e · 7.7GB ·

model
llama
·
7.24B
·
Q8_0
license
MIT License Copyright (c) [year] [fullname] Permission is hereby granted, free of charge, to any per
params
{ "stop": [ "<|system|>", "<|user|>", "<|assistant|>", "</s>"
template
{{- if .System }} <|system|> {{ .System }} </s> {{- end }} <|user|> {{ .Prompt }} </s> <|assistant|>

Readme

zephyr-python-ru

Model Details

Model Description

  • Developed by: C.B. Pronin, A.V. Volosova, A.V. Ostroukh, Yu.N. Strogov, V.V. Kurbatov, A.S. Umarova.
  • Model type: GGUF Conversion and quantizations of model “MexIvanov/zephyr-python-ru-merged” made for ease of inference.
  • Language(s) (NLP): Russian, English, Python
  • License: MIT
  • Finetuned from model: HuggingFaceH4/zephyr-7b-beta

Model Sources

Uses

An experimental finetune of Zephyr-7b-beta, aimed at improving coding performance and support for coding-related instructions written in Russian language.

Direct Use

Instruction-based coding in Python, based of instructions written in natural language (English or Russian)

Prompt template - Zephyr:

<|system|>
</s>
<|user|>
{prompt}</s>
<|assistant|>

Provided files

Tag = Quant method Bits Use case
F16 16 Full F16 weights.
Q8_0 8 Extremely high quality, generally unneeded but max available quant.
Q6_K 6 Very high quality, near perfect, recommended.
Q5_K_M 5 High quality, recommended.
Q4_K_M 4 Good quality, default size for must use cases, recommended.
Q3_K_M 3 Low quality.

Bias, Risks, and Limitations

This adapter model is intended (but not limited) for research usage only. It was trained on a code based instruction set and it does not have any moderation mechanisms. Use at your own risk, we are not responsible for any usage or output of this model.

Quote from Zephyr (base-model) repository: “Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.1), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this.”

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.