Llama-3.2-1B-Instruct lineage
According to the model card, the model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct.
Open Source Model Profile · Grogros
Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-1e5
Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-1e5 is a 1.24B-parameter Llama text-generation fine-tune from Grogros. According to the model card, it fine-tunes meta-llama/Llama-3.2-1B-Instruct.
- Publisher
- Grogros
- Task
- text-generation
- Model type
- llama
- License
- llama3.2
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-1e5 is published by Grogros as a Llama text-generation model. The captured configuration identifies LlamaForCausalLM with model type llama, and Safetensors metadata reports 1,235,814,400 parameters. According to the model card, it is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct, with card data recording llama3.2.
Recorded capabilities
Documented Adafactor training setup
According to the model card, training used learning rate 2e-05, batch sizes 32 and 8, cosine scheduling with 0.1 warmup ratio, seed 42, and 2,000 training steps.
Transformers text-generation record
The captured configuration identifies LlamaForCausalLM with model type llama and Transformers support, with about 1.24B Safetensors parameters.
Use cases in the source record
- Instruction-style text-generation experiments building on the documented Llama-3.2-1B-Instruct lineage.
- Inspection or reproduction of the publisher-documented 2,000-step Adafactor training configuration.
Limitations and unknowns
- According to the model card, intended uses, limitations, and training and evaluation data are recorded as needing more information.
- No evaluation results or context-window value were extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
Source and provenance
Source: Grogros/Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-1e5
Captured: Unknown. Processed: 2026-09-07T19:35:05.675405+00:00.
Llama-3.2-1B-Instruct-activation-alpaca-3.0-AlpacaPoison-1e5 This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct 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: 2e-05 train_batch_size: 32 eval_batch_size: 8 seed: 42 optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments lr_scheduler_type: cosine lr_scheduler_warmup_ratio: 0.1 training_steps: 2000…
F001F002F003F004F005F006F007F008F010F011F012