commit e73f2f89171d1edebcc4d131081c0a614cb5ab80 Author: ModelHub XC Date: Wed Apr 22 00:24:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: afrideva/zephyr-220m-sft-full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bddf87 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.fp16.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +zephyr-220m-sft-full.q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5973fef --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: BEE-spoke-data/zephyr-220m-sft-full +datasets: +- HuggingFaceH4/ultrachat_200k +inference: false +license: apache-2.0 +model-index: +- name: zephyr-220m-sft-full + results: [] +model_creator: BEE-spoke-data +model_name: zephyr-220m-sft-full +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 +--- +# BEE-spoke-data/zephyr-220m-sft-full-GGUF + +Quantized GGUF model files for [zephyr-220m-sft-full](https://huggingface.co/BEE-spoke-data/zephyr-220m-sft-full) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data) + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [zephyr-220m-sft-full.fp16.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.fp16.gguf) | fp16 | 436.50 MB | +| [zephyr-220m-sft-full.q2_k.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q2_k.gguf) | q2_k | 94.43 MB | +| [zephyr-220m-sft-full.q3_k_m.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q3_k_m.gguf) | q3_k_m | 114.65 MB | +| [zephyr-220m-sft-full.q4_k_m.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q4_k_m.gguf) | q4_k_m | 137.58 MB | +| [zephyr-220m-sft-full.q5_k_m.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q5_k_m.gguf) | q5_k_m | 157.91 MB | +| [zephyr-220m-sft-full.q6_k.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q6_k.gguf) | q6_k | 179.52 MB | +| [zephyr-220m-sft-full.q8_0.gguf](https://huggingface.co/afrideva/zephyr-220m-sft-full-GGUF/resolve/main/zephyr-220m-sft-full.q8_0.gguf) | q8_0 | 232.28 MB | + + + +## Original Model Card: + + +# zephyr-220m-sft-full + +This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/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 \ No newline at end of file diff --git a/zephyr-220m-sft-full.fp16.gguf b/zephyr-220m-sft-full.fp16.gguf new file mode 100644 index 0000000..7e184ad --- /dev/null +++ b/zephyr-220m-sft-full.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30bb7d8a9902de884127d773b0234efb94f5a34d97a577902f3fe10758f79382 +size 436502720 diff --git a/zephyr-220m-sft-full.q2_k.gguf b/zephyr-220m-sft-full.q2_k.gguf new file mode 100644 index 0000000..5579fe4 --- /dev/null +++ b/zephyr-220m-sft-full.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614c93a26e6a14b0f62b1f6c185fb97e203f412b07007a2c3052b9b1dc761a5a +size 94430432 diff --git a/zephyr-220m-sft-full.q3_k_m.gguf b/zephyr-220m-sft-full.q3_k_m.gguf new file mode 100644 index 0000000..dac627b --- /dev/null +++ b/zephyr-220m-sft-full.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bb1018df97fedd1d7697e4881103738a3e6e0af4e1d1520f3fd9980837e37e +size 114651360 diff --git a/zephyr-220m-sft-full.q4_k_m.gguf b/zephyr-220m-sft-full.q4_k_m.gguf new file mode 100644 index 0000000..40336b3 --- /dev/null +++ b/zephyr-220m-sft-full.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ba37270a4c52d5d50d668ae84a61282bb055ec189875085f91b14863e74547b +size 137581792 diff --git a/zephyr-220m-sft-full.q5_k_m.gguf b/zephyr-220m-sft-full.q5_k_m.gguf new file mode 100644 index 0000000..aa6eac8 --- /dev/null +++ b/zephyr-220m-sft-full.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19fb8dc52d906f8e388dd2d2b0ab9534dd247ce06c5ab08721c0087b7eb7000b +size 157914336 diff --git a/zephyr-220m-sft-full.q6_k.gguf b/zephyr-220m-sft-full.q6_k.gguf new file mode 100644 index 0000000..b7ac0bd --- /dev/null +++ b/zephyr-220m-sft-full.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb3ba93db0e185bc251527a3a4ea7121866611b781bb309b419a38a310c265e +size 179517664 diff --git a/zephyr-220m-sft-full.q8_0.gguf b/zephyr-220m-sft-full.q8_0.gguf new file mode 100644 index 0000000..6ef5e73 --- /dev/null +++ b/zephyr-220m-sft-full.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7fabb2d8d491d149601517b58fd9baa02aa7662e0103a747b39b45b5e579b62 +size 232276192