👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord. Model creator: InternLM Original model: AlchemistCoder-DS-6.7B GGUF quantization: provided by bartowski based on llama.cpp release b3024 AlchemistCoder is a series of coding models by InternLM. This model is tuned from the DeepSeek coder model, and should excel at all coding related tasks. Under the hood, the model will see a prompt that’s formatted like so: — AlchemistPrompts: Designed as data-specific prompts for harmonizing inherent conflicts in multi-source data and mitigating the instruction/response misalignment at a fined-grained level. — Code Comprehenstion Tasks: Sourced from the process of data construction, consisting of instruction evolution, data filtering, and code review. — Harmonized Multi-source Data: Instruction tuned on 200M tokens, including 6 types of high-quality data. — Superior Model Performance: Surpassing all the open-source models of the same size (6.7/7B), and rivaling or even beating larger models (15B/33B/70B/ChatGPT) on 6 code benchmarks. — Advanced generic capabilities: Demonstrated by the significant improvements…
Модальности:
Генерация текста
Области применения:
Диалог / чат Генерация кода
Задача: Генерация текста
Автор: lmstudio-community
Теги: gguf, code generation, endpoints_compatible, imatrix, conversational
Лайков: 3 | Загрузок: 632
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
