3.21B Llama scale
Captured config identifies LlamaForCausalLM and Safetensors metadata reports 3212749824 parameters.
Open Source Model Profile · Goekdeniz-Guelmez
Josiefied-Hermes-3-Llama-3.2-3B-v1
Josiefied-Hermes-3-Llama-3.2-3B-v1 is a 3.21B-parameter Llama text-generation fine-tune from Goekdeniz-Guelmez. Its card describes JOSIEFIED tuning and a Josie system prompt.
- Publisher
- Goekdeniz-Guelmez
- Task
- text-generation
- Model type
- llama
- License
- Unknown
- Library
- Unknown
- Publication status
- Accepted · not indexed
Model overview
Josiefied-Hermes-3-Llama-3.2-3B-v1 is published by Goekdeniz-Guelmez as a chat-oriented text-generation model. The captured configuration identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 3212749824 parameters. Hub tags associate it with NousResearch/Hermes-3-Llama-3.2-3B as base and fine-tune.
Recorded capabilities
Hermes-3 lineage tags
Hub tags list NousResearch/Hermes-3-Llama-3.2-3B as base model and fine-tune.
Publisher-described JOSIEFIED tuning
According to the model card, the JOSIEFIED family is further fine-tuned for uncensored behavior while retaining tool usage and instruction following.
Documented Josie system prompt
According to the model card, the recommended prompt presents the assistant as J.O.S.I.E., short Josie, with the publisher's wording.
Use cases in the source record
- Chat-style text generation consistent with the captured chat, conversational, and text-generation tags.
Limitations and unknowns
- No license value was extracted from this record.
- No evaluation scores were extracted; the card's outperformance statement is an unverified publisher claim.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Uncensored-behavior and capability descriptions come from the publisher card and have not been independently verified by Ethen.
Source and provenance
Source: Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1
Captured: Unknown. Processed: 2026-09-07T19:35:39.722687+00:00.
JOSIEFIED Model Family The JOSIEFIED model family represents a series of highly advanced language models built upon renowned architectures such as Alibaba’s Qwen2/2.5/3, Google’s Gemma3, and Meta’s LLaMA3/4. Covering sizes from 0.5B to 32B parameters, this model hase been further fine-tuned to maximize uncensored behavior without compromising tool usage or instruction-following abilities. Despite their rebellious spirit, the JOSIEFIED models often outperform their base counterparts on standard benchmarks — delivering both raw power and utility. These models are intended for advanced users who require unrestricted, high-performance l…
F001F002F003F004F005F006F007F008F009F010F011F013