OTel-LLM-8B-A1B-IT is an 8 billion parameter instruction-tuned large language model hosted on Hugging Face. It belongs to the class of foundation models and includes a chat template configured with specific tokens for beginning-of-sequence, end-of-sequence, and padding along with support for a Jinja-based template that handles argument formatting and multimodal content parsing for text and image inputs.
The model defines a tokenizer configuration that sets the end-of-sequence token to "<|im_end|", the pad token to "<|pad|", and disables any default system prompt. Its template logic processes content arrays by checking item types, inserting image placeholders when appropriate, extracting text directly, or converting other items to JSON strings. These details appear directly in the repository's configuration files.
The model is delivered as an open repository on the Hugging Face platform, where users can access the model weights, tokenizer, and associated template code. No pricing, licensing terms, or specific target audience beyond the general Hugging Face community are stated in the available repository metadata.
OTel LLM 8B A1B IT is a Foundation models & chat product. It focuses on providing an open, instruction-tuned large language model for text generation and tool integration. OTel LLM 8B A1B IT is an open-source project aimed at AI developers and researchers. The project is open source (Open Source). The product ships for the web, the command line, and API, and it can be self-hosted.
farbodtavakkoli builds and maintains OTel LLM 8B A1B IT, and the product first shipped in 2024. Among its 5 catalogued features are text generation, tool calling, and open weights.
Latest indexed changes and source events
farbodtavakkoli/OTel-LLM-8B-A1B-IT verified by the PulseGate indexer
Other apps tracked under the same category.
