You can deploy this model and start earning money today!

RichardErkhov/
nnheui_-_pythia-410m-sft-full-gguf

Name: nnheui_-_pythia-410m-sft-full-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

pythia-410m-sft-full - GGUF

Model creator: https://huggingface.co/nnheui/
Original model: https://huggingface.co/nnheui/pythia-410m-sft-full/

Name	Quant method	Size
pythia-410m-sft-full.Q2_K.gguf	Q2_K	0.16GB
pythia-410m-sft-full.IQ3_XS.gguf	IQ3_XS	0.18GB
pythia-410m-sft-full.IQ3_S.gguf	IQ3_S	0.18GB
pythia-410m-sft-full.Q3_K_S.gguf	Q3_K_S	0.18GB
pythia-410m-sft-full.IQ3_M.gguf	IQ3_M	0.2GB
pythia-410m-sft-full.Q3_K.gguf	Q3_K	0.21GB
pythia-410m-sft-full.Q3_K_M.gguf	Q3_K_M	0.21GB
pythia-410m-sft-full.Q3_K_L.gguf	Q3_K_L	0.22GB
pythia-410m-sft-full.IQ4_XS.gguf	IQ4_XS	0.22GB
pythia-410m-sft-full.Q4_0.gguf	Q4_0	0.23GB
pythia-410m-sft-full.IQ4_NL.gguf	IQ4_NL	0.23GB
pythia-410m-sft-full.Q4_K_S.gguf	Q4_K_S	0.23GB
pythia-410m-sft-full.Q4_K.gguf	Q4_K	0.25GB
pythia-410m-sft-full.Q4_K_M.gguf	Q4_K_M	0.25GB
pythia-410m-sft-full.Q4_1.gguf	Q4_1	0.25GB
pythia-410m-sft-full.Q5_0.gguf	Q5_0	0.27GB
pythia-410m-sft-full.Q5_K_S.gguf	Q5_K_S	0.27GB
pythia-410m-sft-full.Q5_K.gguf	Q5_K	0.28GB
pythia-410m-sft-full.Q5_K_M.gguf	Q5_K_M	0.28GB
pythia-410m-sft-full.Q5_1.gguf	Q5_1	0.29GB
pythia-410m-sft-full.Q6_K.gguf	Q6_K	0.31GB
pythia-410m-sft-full.Q8_0.gguf	Q8_0	0.4GB

Original model description:

license: apache-2.0 tags:

alignment-handbook
generated_from_trainer datasets:
HuggingFaceH4/ultrachat_200k base_model: EleutherAI/pythia-410m model-index:
name: pythia-410m-sft-full results: []

pythia-410m-sft-full

This model is a fine-tuned version of EleutherAI/pythia-410m on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

Loss: 1.5227

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: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 256
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
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.5136	1.0	500	1.5227

Framework versions

Transformers 4.36.2
Pytorch 2.2.1
Datasets 2.14.6
Tokenizers 0.15.2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	31.12
AI2 Reasoning Challenge (25-Shot)	26.54
HellaSwag (10-Shot)	40.00
MMLU (5-Shot)	25.49
TruthfulQA (0-shot)	40.21
Winogrande (5-shot)	53.43
GSM8k (5-shot)	1.06

RichardErkhov/nnheui_-_pythia-410m-sft-full-gguf

Original model description:

pythia-410m-sft-full

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Open LLM Leaderboard Evaluation Results

RichardErkhov/
nnheui_-_pythia-410m-sft-full-gguf