RichardErkhov/mlfoundations-dev_-_test_model_revision-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

test_model_revision - GGUF

• Model creator: https://huggingface.co/mlfoundations-dev/
• Original model: https://huggingface.co/mlfoundations-dev/test_model_revision/

Name	Quant method	Size
test_model_revision.Q2_K.gguf	Q2_K	0.0GB
test_model_revision.IQ3_XS.gguf	IQ3_XS	0.0GB
test_model_revision.IQ3_S.gguf	IQ3_S	0.0GB
test_model_revision.Q3_K_S.gguf	Q3_K_S	0.0GB
test_model_revision.IQ3_M.gguf	IQ3_M	0.0GB
test_model_revision.Q3_K.gguf	Q3_K	0.0GB
test_model_revision.Q3_K_M.gguf	Q3_K_M	0.0GB
test_model_revision.Q3_K_L.gguf	Q3_K_L	0.0GB
test_model_revision.IQ4_XS.gguf	IQ4_XS	0.0GB
test_model_revision.Q4_0.gguf	Q4_0	0.0GB
test_model_revision.IQ4_NL.gguf	IQ4_NL	0.0GB
test_model_revision.Q4_K_S.gguf	Q4_K_S	0.0GB
test_model_revision.Q4_K.gguf	Q4_K	0.0GB
test_model_revision.Q4_K_M.gguf	Q4_K_M	0.0GB
test_model_revision.Q4_1.gguf	Q4_1	0.0GB
test_model_revision.Q5_0.gguf	Q5_0	0.0GB
test_model_revision.Q5_K_S.gguf	Q5_K_S	0.0GB
test_model_revision.Q5_K.gguf	Q5_K	0.0GB
test_model_revision.Q5_K_M.gguf	Q5_K_M	0.0GB
test_model_revision.Q5_1.gguf	Q5_1	0.0GB
test_model_revision.Q6_K.gguf	Q6_K	0.0GB
test_model_revision.Q8_0.gguf	Q8_0	0.0GB

Original model description:

library_name: transformers license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags: - llama-factory - full - generated_from_trainer model-index: - name: test_model_revision results: []

test_model_revision

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the llamafactory/alpaca_en dataset. It achieves the following results on the evaluation set:

• Loss: nan

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: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 4
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0003	1	nan

Framework versions

• Transformers 4.45.0
• Pytorch 2.5.0+cu124
• Datasets 2.19.2
• Tokenizers 0.20.0