Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Grogros

Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat-PT2

This Grogros release is a 1.24B-parameter Llama text-generation fine-tune with documented hyperparameters and Llama3.2 licensing.

Publisher
Grogros
Task
text-generation
Model type
llama
License
llama3.2
Library
transformers
Publication status
Accepted · not indexed

Model overview

This Grogros release is a Llama-family text-generation fine-tune. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 1,235,814,400 parameters. According to the model card, it is a fine-tune of Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat on the None dataset.

Recorded capabilities

1.24B Llama record

Captured configuration records LlamaForCausalLM and Safetensors metadata reports 1,235,814,400 parameters.

Named fine-tune lineage

According to the model card and hub tags, the release is presented as a fine-tune of Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat.

Documented hyperparameters

According to the model card, training used learning rate 1e-05, batch sizes 16 and 8, seed 42, multi-GPU distribution, Adafactor, cosine scheduling, and 500 training steps.

Llama3.2 license record

Card data records llama3.2.

Use cases in the source record

  • Conversational text-generation experimentation within the documented Llama3.2 license scope.
  • Lineage and hyperparameter review for users comparing this fine-tune against its named parent revision.

Limitations and unknowns

  • According to the model card, intended uses, limitations, and training and evaluation data are recorded as More information needed.
  • No evaluation results, context-window value, or hardware requirements were extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat-PT2

Captured: Unknown. Processed: 2026-09-07T19:35:05.753496+00:00.

Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat-PT2 This model is a fine-tuned version of Grogros/Llama-3.2-1B-Instruct-distillation-SecretSauceLongJail-5.0-HarmfulLLMLat on the None dataset. Model description More information needed Intended uses & limitations More information needed Training and evaluation data More information needed Training procedure Training hyperparameters The following hyperparameters were used during training: learning_rate: 1e-05 train_batch_size: 16 eval_batch_size: 8 seed: 42 distributed_type: multi-GPU optimizer: Use adafactor and the args are: No additional optimizer arguments…

F001F002F003F004F005F006F007F008F009F010F011F012