Downloads · 30 days
95
3% of all-time downloads
BEE-spoke-data_-_zephyr-220m-sft-full-gguf
RichardErkhov/BEE-spoke-data_-_zephyr-220m-sft-full-gguf
BEE-spoke-data_-_zephyr-220m-sft-full-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
2.9K
Public
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf3 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 25, 2024
- Updated
- Jun 25, 2024
- SHA
- 410355c6
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
zephyr-220m-sft-full - GGUF
- Model creator: https://huggingface.co/BEE-spoke-data/
- Original model: https://huggingface.co/BEE-spoke-data/zephyr-220m-sft-full/
| Name | Quant method | Size |
|---|---|---|
| zephyr-220m-sft-full.Q2_K.gguf | Q2_K | 0.09GB |
| zephyr-220m-sft-full.IQ3_XS.gguf | IQ3_XS | 0.1GB |
| zephyr-220m-sft-full.IQ3_S.gguf | IQ3_S | 0.1GB |
| zephyr-220m-sft-full.Q3_K_S.gguf | Q3_K_S | 0.1GB |
| zephyr-220m-sft-full.IQ3_M.gguf | IQ3_M | 0.1GB |
| zephyr-220m-sft-full.Q3_K.gguf | Q3_K | 0.11GB |
| zephyr-220m-sft-full.Q3_K_M.gguf | Q3_K_M | 0.11GB |
| zephyr-220m-sft-full.Q3_K_L.gguf | Q3_K_L | 0.11GB |
| zephyr-220m-sft-full.IQ4_XS.gguf | IQ4_XS | 0.12GB |
| zephyr-220m-sft-full.Q4_0.gguf | Q4_0 | 0.12GB |
| zephyr-220m-sft-full.IQ4_NL.gguf | IQ4_NL | 0.12GB |
| zephyr-220m-sft-full.Q4_K_S.gguf | Q4_K_S | 0.12GB |
| zephyr-220m-sft-full.Q4_K.gguf | Q4_K | 0.13GB |
| zephyr-220m-sft-full.Q4_K_M.gguf | Q4_K_M | 0.13GB |
| zephyr-220m-sft-full.Q4_1.gguf | Q4_1 | 0.13GB |
| zephyr-220m-sft-full.Q5_0.gguf | Q5_0 | 0.14GB |
| zephyr-220m-sft-full.Q5_K_S.gguf | Q5_K_S | 0.14GB |
| zephyr-220m-sft-full.Q5_K.gguf | Q5_K | 0.15GB |
| zephyr-220m-sft-full.Q5_K_M.gguf | Q5_K_M | 0.15GB |
| zephyr-220m-sft-full.Q5_1.gguf | Q5_1 | 0.16GB |
| zephyr-220m-sft-full.Q6_K.gguf | Q6_K | 0.17GB |
| zephyr-220m-sft-full.Q8_0.gguf | Q8_0 | 0.22GB |
Original model description:
license: apache-2.0 base_model: BEE-spoke-data/smol_llama-220M-openhermes tags:
- generated_from_trainer model-index:
- name: zephyr-220m-sft-full results: [] datasets:
- HuggingFaceH4/ultrachat_200k
<!-- 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. -->
zephyr-220m-sft-full
This model is a fine-tuned version of BEE-spoke-data/smol_llama-220M-openhermes on the Ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.6579
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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6447 | 1.0 | 1624 | 1.6579 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince
- Created
- Jun 25, 2024
- Updated
- Jun 25, 2024