nnheui_-_stablelm-2-1_6b-sft-full-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
nnheui_-_stablelm-2-1_6b-sft-full-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

stablelm-2-1_6b-sft-full - GGUF

Model creator: https://huggingface.co/nnheui/
Original model: https://huggingface.co/nnheui/stablelm-2-1_6b-sft-full/

Name	Quant method	Size
stablelm-2-1_6b-sft-full.Q2_K.gguf	Q2_K	0.65GB
stablelm-2-1_6b-sft-full.IQ3_XS.gguf	IQ3_XS	0.71GB
stablelm-2-1_6b-sft-full.IQ3_S.gguf	IQ3_S	0.74GB
stablelm-2-1_6b-sft-full.Q3_K_S.gguf	Q3_K_S	0.74GB
stablelm-2-1_6b-sft-full.IQ3_M.gguf	IQ3_M	0.77GB
stablelm-2-1_6b-sft-full.Q3_K.gguf	Q3_K	0.8GB
stablelm-2-1_6b-sft-full.Q3_K_M.gguf	Q3_K_M	0.8GB
stablelm-2-1_6b-sft-full.Q3_K_L.gguf	Q3_K_L	0.85GB
stablelm-2-1_6b-sft-full.IQ4_XS.gguf	IQ4_XS	0.88GB
stablelm-2-1_6b-sft-full.Q4_0.gguf	Q4_0	0.92GB
stablelm-2-1_6b-sft-full.IQ4_NL.gguf	IQ4_NL	0.92GB
stablelm-2-1_6b-sft-full.Q4_K_S.gguf	Q4_K_S	0.92GB
stablelm-2-1_6b-sft-full.Q4_K.gguf	Q4_K	0.96GB
stablelm-2-1_6b-sft-full.Q4_K_M.gguf	Q4_K_M	0.96GB
stablelm-2-1_6b-sft-full.Q4_1.gguf	Q4_1	1.0GB
stablelm-2-1_6b-sft-full.Q5_0.gguf	Q5_0	1.08GB
stablelm-2-1_6b-sft-full.Q5_K_S.gguf	Q5_K_S	1.08GB
stablelm-2-1_6b-sft-full.Q5_K.gguf	Q5_K	1.11GB
stablelm-2-1_6b-sft-full.Q5_K_M.gguf	Q5_K_M	1.11GB
stablelm-2-1_6b-sft-full.Q5_1.gguf	Q5_1	1.17GB
stablelm-2-1_6b-sft-full.Q6_K.gguf	Q6_K	1.26GB
stablelm-2-1_6b-sft-full.Q8_0.gguf	Q8_0	1.63GB

Original model description:

license: other base_model: stabilityai/stablelm-2-1_6b tags:

alignment-handbook
trl
sft
generated_from_trainer
trl
sft
generated_from_trainer datasets:
HuggingFaceH4/ultrachat_200k model-index:
name: stablelm-2-1_6b-sft-full results: []

stablelm-2-1_6b-sft-full

This model is a fine-tuned version of stabilityai/stablelm-2-1_6b on the HuggingFaceH4/ultrachat_200k 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: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 16
total_train_batch_size: 128
total_eval_batch_size: 16
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

Framework versions

Transformers 4.40.0
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.19.1