Llama 3.2 1B-class fine-tune
The model is recorded as LlamaForCausalLM with about 1.24B parameters, and the model card identifies meta-llama/Llama-3.2-1B-Instruct as its starting point.
Open Source Model Profile · Erioh
fine-tuned-model
fine-tuned-model is a 1.24B-parameter Llama fine-tune from Erioh. According to the model card, it starts from Llama-3.2-1B-Instruct and trains on the marsyas/gtzan dataset.
- Publisher
- Erioh
- Task
- text-generation
- Model type
- llama
- License
- llama3.2
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
fine-tuned-model is published by Erioh as a Llama text-generation fine-tune. Captured metadata reports 1,235,814,400 parameters with LlamaForCausalLM, and card data records llama3.2. According to the model card, it is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct trained on the marsyas/gtzan dataset.
Recorded capabilities
Llama3.2 licensing record
Card data records llama3.2 for this model.
GTZAN dataset fine-tuning
According to the model card, the model was fine-tuned on the marsyas/gtzan dataset.
Publisher-reported training trace
According to the model card, training used 10 epochs with documented hyperparameters and reported an evaluation loss of 1.3441.
Use cases in the source record
- Conversational text-generation experiments starting from a documented Llama-3.2-1B-Instruct fine-tune.
- Training-replication study using the card's published hyperparameters and reported loss trace.
Limitations and unknowns
- No context-window value was extracted from this record.
- No independent benchmark evaluations were extracted; the reported loss figure is a publisher claim.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- Intended uses, limitations, and training-data details are recorded as needing more information in the model card.
Source and provenance
Source: Erioh/fine-tuned-model
Captured: Unknown. Processed: 2026-09-07T19:35:05.430829+00:00.
Erioh/finetuned-model This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the marsyas/gtzan dataset. It achieves the following results on the evaluation set: Loss: 1.3441 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: 4 eval_batch_size: 2 seed: 42 optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer argu…
F001F002F003F004F005F006F007F009F010F011F012F013