You can deploy this model and start earning money today!

RichardErkhov/
HuggingFaceH4_-_starchat2-15b-sft-v0.1-gguf

Name: HuggingFaceH4_-_starchat2-15b-sft-v0.1-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

starchat2-15b-sft-v0.1 - GGUF

Model creator: https://huggingface.co/HuggingFaceH4/
Original model: https://huggingface.co/HuggingFaceH4/starchat2-15b-sft-v0.1/

Name	Quant method	Size
starchat2-15b-sft-v0.1.Q2_K.gguf	Q2_K	5.77GB
starchat2-15b-sft-v0.1.IQ3_XS.gguf	IQ3_XS	6.25GB
starchat2-15b-sft-v0.1.IQ3_S.gguf	IQ3_S	6.52GB
starchat2-15b-sft-v0.1.Q3_K_S.gguf	Q3_K_S	6.51GB
starchat2-15b-sft-v0.1.IQ3_M.gguf	IQ3_M	6.8GB
starchat2-15b-sft-v0.1.Q3_K.gguf	Q3_K	7.49GB
starchat2-15b-sft-v0.1.Q3_K_M.gguf	Q3_K_M	7.49GB
starchat2-15b-sft-v0.1.Q3_K_L.gguf	Q3_K_L	8.35GB
starchat2-15b-sft-v0.1.IQ4_XS.gguf	IQ4_XS	8.12GB
starchat2-15b-sft-v0.1.Q4_0.gguf	Q4_0	8.44GB
starchat2-15b-sft-v0.1.IQ4_NL.gguf	IQ4_NL	8.55GB
starchat2-15b-sft-v0.1.Q4_K_S.gguf	Q4_K_S	8.53GB
starchat2-15b-sft-v0.1.Q4_K.gguf	Q4_K	9.18GB
starchat2-15b-sft-v0.1.Q4_K_M.gguf	Q4_K_M	9.18GB
starchat2-15b-sft-v0.1.Q4_1.gguf	Q4_1	9.35GB
starchat2-15b-sft-v0.1.Q5_0.gguf	Q5_0	10.27GB
starchat2-15b-sft-v0.1.Q5_K_S.gguf	Q5_K_S	10.27GB
starchat2-15b-sft-v0.1.Q5_K.gguf	Q5_K	10.65GB
starchat2-15b-sft-v0.1.Q5_K_M.gguf	Q5_K_M	10.65GB
starchat2-15b-sft-v0.1.Q5_1.gguf	Q5_1	11.18GB
starchat2-15b-sft-v0.1.Q6_K.gguf	Q6_K	12.2GB

Original model description:

license: bigcode-openrail-m base_model: bigcode/starcoder2-15b tags:

alignment-handbook
generated_from_trainer datasets:
HuggingFaceH4/airoboros-3.2
HuggingFaceH4/Code-Feedback
HuggingFaceH4/orca-math-word-problems-200k
HuggingFaceH4/SystemChat
HuggingFaceH4/capybara model-index:
name: starcoder2-15b-sft-v5.0 results: []

Model Card for starchat2-15b-sft-v0.1

This model is a fine-tuned version of bigcode/starcoder2-15b on the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets. It achieves the following results on the evaluation set:

Loss: 0.6614

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: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 16
total_train_batch_size: 128
total_eval_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.6422	1.0	910	0.6910
0.5701	2.0	1820	0.6639
0.5227	3.0	2730	0.6614

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.1

RichardErkhov/HuggingFaceH4_-_starchat2-15b-sft-v0.1-gguf

Original model description:

Model Card for starchat2-15b-sft-v0.1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
HuggingFaceH4_-_starchat2-15b-sft-v0.1-gguf