Downloads · 30 days
69
4% of all-time downloads
tanliboy_-_zephyr-gemma-2-9b-sft-gguf
RichardErkhov/tanliboy_-_zephyr-gemma-2-9b-sft-gguf
tanliboy_-_zephyr-gemma-2-9b-sft-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
108 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf119 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024
- SHA
- 832e731d
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
zephyr-gemma-2-9b-sft - GGUF
- Model creator: https://huggingface.co/tanliboy/
- Original model: https://huggingface.co/tanliboy/zephyr-gemma-2-9b-sft/
| Name | Quant method | Size |
|---|---|---|
| zephyr-gemma-2-9b-sft.Q2_K.gguf | Q2_K | 3.54GB |
| zephyr-gemma-2-9b-sft.IQ3_XS.gguf | IQ3_XS | 3.86GB |
| zephyr-gemma-2-9b-sft.IQ3_S.gguf | IQ3_S | 4.04GB |
| zephyr-gemma-2-9b-sft.Q3_K_S.gguf | Q3_K_S | 4.04GB |
| zephyr-gemma-2-9b-sft.IQ3_M.gguf | IQ3_M | 4.19GB |
| zephyr-gemma-2-9b-sft.Q3_K.gguf | Q3_K | 4.43GB |
| zephyr-gemma-2-9b-sft.Q3_K_M.gguf | Q3_K_M | 4.43GB |
| zephyr-gemma-2-9b-sft.Q3_K_L.gguf | Q3_K_L | 4.78GB |
| zephyr-gemma-2-9b-sft.IQ4_XS.gguf | IQ4_XS | 4.86GB |
| zephyr-gemma-2-9b-sft.Q4_0.gguf | Q4_0 | 5.07GB |
| zephyr-gemma-2-9b-sft.IQ4_NL.gguf | IQ4_NL | 5.1GB |
| zephyr-gemma-2-9b-sft.Q4_K_S.gguf | Q4_K_S | 5.1GB |
| zephyr-gemma-2-9b-sft.Q4_K.gguf | Q4_K | 5.37GB |
| zephyr-gemma-2-9b-sft.Q4_K_M.gguf | Q4_K_M | 5.37GB |
| zephyr-gemma-2-9b-sft.Q4_1.gguf | Q4_1 | 5.55GB |
| zephyr-gemma-2-9b-sft.Q5_0.gguf | Q5_0 | 6.04GB |
| zephyr-gemma-2-9b-sft.Q5_K_S.gguf | Q5_K_S | 0.01GB |
| zephyr-gemma-2-9b-sft.Q5_K.gguf | Q5_K | 6.19GB |
| zephyr-gemma-2-9b-sft.Q5_K_M.gguf | Q5_K_M | 6.19GB |
| zephyr-gemma-2-9b-sft.Q5_1.gguf | Q5_1 | 6.52GB |
| zephyr-gemma-2-9b-sft.Q6_K.gguf | Q6_K | 7.07GB |
| zephyr-gemma-2-9b-sft.Q8_0.gguf | Q8_0 | 9.15GB |
Original model description:
license: gemma base_model: google/gemma-2-9b tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer datasets:
- HuggingFaceH4/ultrachat_200k model-index:
- name: zephyr-gemma-2-9b-sft results: []
<!-- 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-gemma-2-9b-sft
This model is a fine-tuned version of google/gemma-2-9b on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:
- Loss: 1.0639
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0962 | 0.9995 | 951 | 1.0639 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Created
- Aug 23, 2024
- Updated
- Aug 23, 2024