Downloads · 30 days
222
12% of all-time downloads
PracticeLLM_-_KoSOLAR-Platypus-10.7B-gguf
RichardErkhov/PracticeLLM_-_KoSOLAR-Platypus-10.7B-gguf
PracticeLLM_-_KoSOLAR-Platypus-10.7B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.8K
Public
Repo size
123 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf142 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 27, 2024
- Updated
- Jul 27, 2024
- SHA
- 2c749551
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
KoSOLAR-Platypus-10.7B - GGUF
- Model creator: https://huggingface.co/PracticeLLM/
- Original model: https://huggingface.co/PracticeLLM/KoSOLAR-Platypus-10.7B/
| Name | Quant method | Size |
|---|---|---|
| KoSOLAR-Platypus-10.7B.Q2_K.gguf | Q2_K | 3.77GB |
| KoSOLAR-Platypus-10.7B.IQ3_XS.gguf | IQ3_XS | 4.18GB |
| KoSOLAR-Platypus-10.7B.IQ3_S.gguf | IQ3_S | 4.41GB |
| KoSOLAR-Platypus-10.7B.Q3_K_S.gguf | Q3_K_S | 4.39GB |
| KoSOLAR-Platypus-10.7B.IQ3_M.gguf | IQ3_M | 4.56GB |
| KoSOLAR-Platypus-10.7B.Q3_K.gguf | Q3_K | 4.88GB |
| KoSOLAR-Platypus-10.7B.Q3_K_M.gguf | Q3_K_M | 4.88GB |
| KoSOLAR-Platypus-10.7B.Q3_K_L.gguf | Q3_K_L | 5.31GB |
| KoSOLAR-Platypus-10.7B.IQ4_XS.gguf | IQ4_XS | 5.47GB |
| KoSOLAR-Platypus-10.7B.Q4_0.gguf | Q4_0 | 5.7GB |
| KoSOLAR-Platypus-10.7B.IQ4_NL.gguf | IQ4_NL | 5.77GB |
| KoSOLAR-Platypus-10.7B.Q4_K_S.gguf | Q4_K_S | 5.75GB |
| KoSOLAR-Platypus-10.7B.Q4_K.gguf | Q4_K | 6.07GB |
| KoSOLAR-Platypus-10.7B.Q4_K_M.gguf | Q4_K_M | 6.07GB |
| KoSOLAR-Platypus-10.7B.Q4_1.gguf | Q4_1 | 6.32GB |
| KoSOLAR-Platypus-10.7B.Q5_0.gguf | Q5_0 | 6.94GB |
| KoSOLAR-Platypus-10.7B.Q5_K_S.gguf | Q5_K_S | 6.94GB |
| KoSOLAR-Platypus-10.7B.Q5_K.gguf | Q5_K | 7.13GB |
| KoSOLAR-Platypus-10.7B.Q5_K_M.gguf | Q5_K_M | 7.13GB |
| KoSOLAR-Platypus-10.7B.Q5_1.gguf | Q5_1 | 7.56GB |
| KoSOLAR-Platypus-10.7B.Q6_K.gguf | Q6_K | 8.26GB |
| KoSOLAR-Platypus-10.7B.Q8_0.gguf | Q8_0 | 10.69GB |
Original model description:
language:
- ko library_name: transformers pipeline_tag: text-generation license: cc-by-nc-sa-4.0 datasets:
- kyujinpy/KOR-OpenOrca-Platypus-v3
PracticeLLM/KoSOLAR-Platypus-10.7B
Model Details
Model Developers Kyujin Han (kyujinpy)
Method
LoRA with quantization.
Base Model
yanolja/KoSOLAR-10.7B-v0.2
Dataset
kyujinpy/KOR-OpenOrca-Platypus-v3.
Hyperparameters
python finetune.py \
--base_model yanolja/KoSOLAR-10.7B-v0.2 \
--data-path kyujinpy/KOR-OpenOrca-Platypus-v3 \
--output_dir ./Ko-PlatypusSOLAR-10.7B \
--batch_size 64 \
--micro_batch_size 1 \
--num_epochs 5 \
--learning_rate 2e-5 \
--cutoff_len 2048 \
--val_set_size 0 \
--lora_r 64 \
--lora_alpha 64 \
--lora_dropout 0.05 \
--lora_target_modules '[embed_tokens, q_proj, k_proj, v_proj, o_proj, gate_proj, down_proj, up_proj, lm_head]' \
--train_on_inputs False \
--add_eos_token False \
--group_by_length False \
--prompt_template_name en_simple \
--lr_scheduler 'cosine' \
Share all of things. It is my belief.
Model Benchmark
Open Ko-LLM leaderboard & lm-evaluation-harness(zero-shot)
- Follow up as Ko-link.
| Model | Average | ARC | HellaSwag | MMLU | TruthfulQA | Ko-CommonGenV2 | | --- | --- | --- | --- | --- | --- | --- | | PracticeLLM/KoSOLAR-Platypus-10.7B | --- | --- | --- | --- | --- | --- | | LDCC/LDCC-SOLAR-10.7B | 59.34 | 55.38 | 65.56 | 53.38 | 64.39 | 57.97 | | yanolja/KoSOLAR-10.7B-v0.2 | 55.62 | 50.51 | 62.29 | 53.76 | 47.31 | 64.23 |
| megastudyedu/M-SOLAR-10.7B-v1.3 | 56.64 | 51.37 | 60.93 | 54.91 | 48.45 | 67.53 |
Implementation Code
### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "PracticeLLM/KoSOLAR-Platypus-10.7B"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)
- Created
- Jul 27, 2024
- Updated
- Jul 27, 2024