# WitchLM-1.5B

[Canonical model page](https://headlessthrones.com/models/arcee-ai-witchlm-1-5b) · [Model library](https://headlessthrones.com/models)

Public catalog reference from Headless Thrones. Exact catalog ID: `arcee-ai-witchlm-1-5b`. 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 WitchLM-1.5B

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/arcee-ai-witchlm-1-5b#model-answer-identity) · [Access](https://headlessthrones.com/models/arcee-ai-witchlm-1-5b#model-answer-access) · [License](https://headlessthrones.com/models/arcee-ai-witchlm-1-5b#model-answer-license) · [Model details](https://headlessthrones.com/models/arcee-ai-witchlm-1-5b#model-answer-research) · [Weight details](https://headlessthrones.com/models/arcee-ai-witchlm-1-5b#model-answer-repository)

### Which WitchLM-1.5B does this page describe?

WitchLM-1.5B is a model record from **Arcee AI** in the WitchLM family. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B)

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 WitchLM-1.5B?

The catalog documents **Open weights** access  for WitchLM-1.5B. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B)

As of the catalog check, this version was listed without confirmed general availability. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B)

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 license is recorded for WitchLM-1.5B?

The recorded license label is **apache-2.0**. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B)

Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.

### What distinguishes WitchLM-1.5B?

These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results.

**Base checkpoint**: Fine-tuned from Qwen2 1.5B; no capability, context or cutoff inherited. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/README.md)

**Published training recipe**: Trainer metadata reports five epochs, Adam optimization and a cosine learning-rate schedule. This is training metadata, not evidence of a context limit. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/README.md)

**Recorded software versions**: The generated training card records Transformers 4.44.0, PyTorch 2.3.1 with CUDA 12.1, Datasets 2.20.0 and Tokenizers 0.19.1. [Source](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/README.md)

### What is documented about the WitchLM-1.5B checkpoint?

This evidence refers to `arcee-ai/WitchLM-1.5B` at recorded revision `1b7b514b4043c209cde8dc2910a349b238d892b5`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/arcee-ai/WitchLM-1.5B)

Safetensors metadata records **1,543,714,304 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/arcee-ai/WitchLM-1.5B)

Recorded architecture class: `Qwen2ForCausalLM`. [Repository metadata](https://huggingface.co/api/models/arcee-ai/WitchLM-1.5B)

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/arcee-ai/WitchLM-1.5B)

#### What the configuration file says

The pinned `config.json` contains these values. [Pinned configuration](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/config.json)

`max_position_embeddings`: 131,072

`torch_dtype`: bfloat16

`num_attention_heads`: 12

`num_key_value_heads`: 2

`num_hidden_layers`: 28

`hidden_size`: 1,536

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/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/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/arcee-ai/WitchLM-1.5B) · [Source 2](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/README.md) · [Source 3](https://huggingface.co/arcee-ai/WitchLM-1.5B/resolve/1b7b514b4043c209cde8dc2910a349b238d892b5/config.json)

**Evidence still missing here:** context or input capacity, 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.