afrideva / phi-2_dolly_instruction_polish-GGUF

huggingface.co
Total runs: 843
24-hour runs: 18
7-day runs: 81
30-day runs: 176
Model's Last Updated: December 25 2023
text-generation

Introduction of phi-2_dolly_instruction_polish-GGUF

Model Details of phi-2_dolly_instruction_polish-GGUF

s3nh/phi-2_dolly_instruction_polish-GGUF

Quantized GGUF model files for phi-2_dolly_instruction_polish from s3nh

Original Model Card:

Built with Axolotl

phi-2-sft-out

This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2813
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: 3e-06
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 4
Training results
Training Loss Epoch Step Validation Loss
No log 0.0 1 1.7973
1.9767 0.25 5290 1.4832
1.8474 0.5 10580 1.4356
1.8121 0.75 15870 1.4022
1.8333 1.0 21160 1.3678
1.6601 1.25 26450 1.3508
1.5452 1.5 31740 1.3357
1.7381 1.75 37030 1.3191
1.6256 2.0 42320 1.3090
1.5521 2.25 47610 1.2961
1.8318 2.5 52900 1.2910
1.6761 2.75 58190 1.2901
1.6312 3.0 63480 1.2879
1.7003 3.25 68770 1.2820
1.6915 3.5 74060 1.2814
1.5757 3.75 79350 1.2813
Framework versions
  • Transformers 4.37.0.dev0
  • Pytorch 2.1.2+cu121
  • Datasets 2.16.0
  • Tokenizers 0.15.0
Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: True
  • bnb_4bit_compute_dtype: bfloat16
Framework versions
  • PEFT 0.6.0

Runs of afrideva phi-2_dolly_instruction_polish-GGUF on huggingface.co

843
Total runs
18
24-hour runs
-9
3-day runs
81
7-day runs
176
30-day runs

More Information About phi-2_dolly_instruction_polish-GGUF huggingface.co Model

More phi-2_dolly_instruction_polish-GGUF license Visit here:

https://choosealicense.com/licenses/other

phi-2_dolly_instruction_polish-GGUF huggingface.co

phi-2_dolly_instruction_polish-GGUF huggingface.co is an AI model on huggingface.co that provides phi-2_dolly_instruction_polish-GGUF's model effect (), which can be used instantly with this afrideva phi-2_dolly_instruction_polish-GGUF model. huggingface.co supports a free trial of the phi-2_dolly_instruction_polish-GGUF model, and also provides paid use of the phi-2_dolly_instruction_polish-GGUF. Support call phi-2_dolly_instruction_polish-GGUF model through api, including Node.js, Python, http.

phi-2_dolly_instruction_polish-GGUF huggingface.co Url

https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF

afrideva phi-2_dolly_instruction_polish-GGUF online free

phi-2_dolly_instruction_polish-GGUF huggingface.co is an online trial and call api platform, which integrates phi-2_dolly_instruction_polish-GGUF's modeling effects, including api services, and provides a free online trial of phi-2_dolly_instruction_polish-GGUF, you can try phi-2_dolly_instruction_polish-GGUF online for free by clicking the link below.

afrideva phi-2_dolly_instruction_polish-GGUF online free url in huggingface.co:

https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF

phi-2_dolly_instruction_polish-GGUF install

phi-2_dolly_instruction_polish-GGUF is an open source model from GitHub that offers a free installation service, and any user can find phi-2_dolly_instruction_polish-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of phi-2_dolly_instruction_polish-GGUF install, users can directly use phi-2_dolly_instruction_polish-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

phi-2_dolly_instruction_polish-GGUF install url in huggingface.co:

https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF

Url of phi-2_dolly_instruction_polish-GGUF

phi-2_dolly_instruction_polish-GGUF huggingface.co Url

Provider of phi-2_dolly_instruction_polish-GGUF huggingface.co

afrideva
ORGANIZATIONS

Other API from afrideva

huggingface.co

Total runs: 582
Run Growth: 138
Growth Rate: 23.63%
Updated:December 18 2023
huggingface.co

Total runs: 578
Run Growth: 159
Growth Rate: 27.56%
Updated:December 08 2023