# Yarn-Llama-2-13b-64k [Canonical model page](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `nous-research-yarn-llama-2-13b-64k`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about Yarn-Llama-2-13b-64k AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-identity) · [Access](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-access) · [Token limits](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-context) · [Inputs & outputs](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-modalities) · [Model details](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-research) · [Weight details](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-64k#model-answer-repository) ### Which Yarn-Llama-2-13b-64k does this page describe? Yarn-Llama-2-13b-64k is a model record from **Nous Research** in the Yarn family. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) A separate version identifier is not documented in this record; the model name alone does not establish which snapshot a service runs. ### How can you access Yarn-Llama-2-13b-64k? The catalog documents **Open weights** access for Yarn-Llama-2-13b-64k. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) As of the catalog check, this version was listed without confirmed general availability. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. ### What are Yarn-Llama-2-13b-64k's context and output limits? The publisher reports the context window as **64k tokens**. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) We retain the publisher's notation and qualifiers; no exact token count or hosted serving allowance is inferred from it. A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance. Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity. ### What can Yarn-Llama-2-13b-64k receive and generate? Documented inputs: **text**. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) Documented outputs: **text**. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k) Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation. ### What distinguishes Yarn-Llama-2-13b-64k? These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results. **Long-context training**: Further pretrained for 400 long-context steps using YaRN. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) **Context and training data**: Further pretrained on a PG19 subset to support the documented 64k context window. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) **Runtime dependency**: The released patched checkpoint requires Flash Attention 2. [Source](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) ### What is documented about the Yarn-Llama-2-13b-64k checkpoint? This evidence refers to `NousResearch/Yarn-Llama-2-13b-64k` at recorded revision `e3e00cbcda2313dd662e823134e6505bcf4e2550`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) Recorded architecture class: `LlamaForCausalLM`. [Repository metadata](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) Repository task tag: `text-generation`. A task tag identifies a distribution category; it does not measure performance on that task. [Repository metadata](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) Listed library: `transformers`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) Repository access gate: `false`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) #### What the configuration file says The pinned `config.json` contains these values. [Pinned configuration](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/config.json) `max_position_embeddings`: 65,536 `rope_scaling`: {"factor":16,"original\_max\_position\_embeddings":4096,"type":"yarn","finetuned":true} `torch_dtype`: bfloat16 `num_attention_heads`: 40 `num_key_value_heads`: 40 `num_hidden_layers`: 40 `hidden_size`: 5,120 Configuration values describe the checkpoint and its implementation. In particular, max\_position\_embeddings, sliding\_window and rope\_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior. Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) **Catalog qualifications:** Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. [Source 1](https://huggingface.co/api/models/NousResearch/Yarn-Llama-2-13b-64k) · [Source 2](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/README.md) · [Source 3](https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k/resolve/e3e00cbcda2313dd662e823134e6505bcf4e2550/config.json) **Evidence still missing here:** knowledge and training-data cutoffs and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other Yarn models from Nous Research. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [Yarn-Llama-2-13b-128k](https://headlessthrones.com/models/nous-research-yarn-llama-2-13b-128k) Open weights ### [Yarn-Llama-2-70b-32k](https://headlessthrones.com/models/nous-research-yarn-llama-2-70b-32k) Open weights ### [Yarn-Llama-2-7b-128k](https://headlessthrones.com/models/nous-research-yarn-llama-2-7b-128k) Open weights ### [Yarn-Llama-2-7b-64k](https://headlessthrones.com/models/nous-research-yarn-llama-2-7b-64k) Open weights ### [Yarn-Solar-10b-32k](https://headlessthrones.com/models/nous-research-yarn-solar-10b-32k) Open weights ### [Yarn-Solar-10b-64k](https://headlessthrones.com/models/nous-research-yarn-solar-10b-64k) Open weights