8B-class full-precision source
According to the model card, the repo contains full-precision Safetensors source, with captured metadata reporting about 8.03B parameters on a Llama architecture.
Open Source Model Profile · DavidAU
Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored
Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored is an 8.03B-parameter Llama reasoning merge from DavidAU distributed as full-precision Safetensors source.
- Publisher
- DavidAU
- Task
- text-generation
- Model type
- llama
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored is published by DavidAU as a Llama-based text-generation model. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,261,248 parameters. According to the model card, the repo provides full-precision Safetensors source for generating quantized formats, and hub tags record reasoning, merge, and DeepSeek markers.
Recorded capabilities
Reasoning and merge markers
Hub tags record reasoning, thinking, chain-of-thought, DeepSeek, fine-tune, and merge markers alongside the DarkIdol base-model reference.
Quant-generation source
According to the model card, the source supports generating GGUF and other quant formats, with GGUF links noted by the publisher.
Publisher sampler documentation
According to the model card, the publisher documents parameters, samplers, advanced samplers, and context-limit usage notes for the source and quantized versions.
Use cases in the source record
- Quantization work generating GGUF, GPTQ, EXL2, AWQ, or HQQ versions from the publisher's documented Safetensors source.
- Reasoning-style text-generation experiments using the publisher's documented sampler and parameter settings.
Limitations and unknowns
- No license value was extracted from this record.
- No evaluation results were extracted from this record.
- No verified context-window value was extracted; a 128k-context string appears only as a hub tag.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: DavidAU/Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored
Captured: Unknown. Processed: 2026-09-07T19:35:04.478841+00:00.
Llama-3.1-DeepSeek-8B-DarkIdol-Instruct-1.2-Uncensored This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly. (source files will be uploaded when parameter count shows in upper left) NOTE: Links to GGUFs below. IMPORTANT: Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers If you are going to use this model, (source, GGUF or a different quant), please review this document for critical parameter, sampler and advance sampler settings (for multiple AI/LLM aps). This a "Class 1/2" (settings…
F001F002F003F004F005F006F008F009F010F011F012F013F014F015F016