125 lines
4.5 KiB
Markdown
125 lines
4.5 KiB
Markdown
---
|
|
base_model: s3nh/phi-2_dolly_instruction_polish
|
|
inference: false
|
|
library_name: peft
|
|
license: other
|
|
model-index:
|
|
- name: phi-2-sft-out
|
|
results: []
|
|
model_creator: s3nh
|
|
model_name: phi-2_dolly_instruction_polish
|
|
pipeline_tag: text-generation
|
|
quantized_by: afrideva
|
|
tags:
|
|
- generated_from_trainer
|
|
- gguf
|
|
- ggml
|
|
- quantized
|
|
- q2_k
|
|
- q3_k_m
|
|
- q4_k_m
|
|
- q5_k_m
|
|
- q6_k
|
|
- q8_0
|
|
---
|
|
# s3nh/phi-2_dolly_instruction_polish-GGUF
|
|
|
|
Quantized GGUF model files for [phi-2_dolly_instruction_polish](https://huggingface.co/s3nh/phi-2_dolly_instruction_polish) from [s3nh](https://huggingface.co/s3nh)
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [phi-2_dolly_instruction_polish.fp16.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.fp16.gguf) | fp16 | 5.56 GB |
|
|
| [phi-2_dolly_instruction_polish.q2_k.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q2_k.gguf) | q2_k | 1.17 GB |
|
|
| [phi-2_dolly_instruction_polish.q3_k_m.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q3_k_m.gguf) | q3_k_m | 1.48 GB |
|
|
| [phi-2_dolly_instruction_polish.q4_k_m.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q4_k_m.gguf) | q4_k_m | 1.79 GB |
|
|
| [phi-2_dolly_instruction_polish.q5_k_m.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q5_k_m.gguf) | q5_k_m | 2.07 GB |
|
|
| [phi-2_dolly_instruction_polish.q6_k.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q6_k.gguf) | q6_k | 2.29 GB |
|
|
| [phi-2_dolly_instruction_polish.q8_0.gguf](https://huggingface.co/afrideva/phi-2_dolly_instruction_polish-GGUF/resolve/main/phi-2_dolly_instruction_polish.q8_0.gguf) | q8_0 | 2.96 GB |
|
|
|
|
|
|
|
|
## Original Model Card:
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
should probably proofread and complete it, then remove this comment. -->
|
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
|
# phi-2-sft-out
|
|
|
|
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/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 |