commit 977630e17c75db114b3839b7663d592b6a8a384d Author: ModelHub XC Date: Sun Sep 6 12:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..483f44a --- /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 +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9dd9d59 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1 +datasets: +- databricks/databricks-dolly-15k +inference: false +language: +- en +license: apache-2.0 +model_creator: habanoz +model_name: TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1 +pipeline_tag: text-generation +quantized_by: afrideva +tags: +- gguf +- ggml +- quantized +- q2_k +- q3_k_m +- q4_k_m +- q5_k_m +- q6_k +- q8_0 +--- +# habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF + +Quantized GGUF model files for [TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1](https://huggingface.co/habanoz/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1) from [habanoz](https://huggingface.co/habanoz) + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf) | fp16 | 2.20 GB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf) | q2_k | 483.12 MB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf) | q3_k_m | 550.82 MB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf) | q4_k_m | 668.79 MB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf) | q5_k_m | 783.02 MB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf) | q6_k | 904.39 MB | +| [tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-2T-lr-2e-4-3ep-dolly-15k-instruct-v1-GGUF/resolve/main/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf) | q8_0 | 1.17 GB | + + + +## Original Model Card: +TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T finetuned using dolly dataset. + +Training took 1 hour on an 'ml.g5.xlarge' instance. + + +```python +hyperparameters ={ + 'num_train_epochs': 3, # number of training epochs + 'per_device_train_batch_size': 6, # batch size for training + 'gradient_accumulation_steps': 2, # Number of updates steps to accumulate + 'gradient_checkpointing': True, # save memory but slower backward pass + 'bf16': True, # use bfloat16 precision + 'tf32': True, # use tf32 precision + 'learning_rate': 2e-4, # learning rate + 'max_grad_norm': 0.3, # Maximum norm (for gradient clipping) + 'warmup_ratio': 0.03, # warmup ratio + "lr_scheduler_type":"constant", # learning rate scheduler + 'save_strategy': "epoch", # save strategy for checkpoints + "logging_steps": 10, # log every x steps + 'merge_adapters': True, # wether to merge LoRA into the model (needs more memory) + 'use_flash_attn': True, # Whether to use Flash Attention +} + +``` \ No newline at end of file diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf new file mode 100644 index 0000000..62afb61 --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0264e7a9b598a57d4136cc778932ed26e88ce6a0d6b327f598e56d0611eecbd +size 2201989952 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf new file mode 100644 index 0000000..1f12a25 --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24de6f492b2d8350edb3fd176bd2ed41d543ce97d0541ec4f84a0537c4b21068 +size 483115904 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf new file mode 100644 index 0000000..9e5a54d --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b959ba87b14bbc156eb79445be6c46a383ad80a91a2ec674bbc59d402fbcc46 +size 550818688 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf new file mode 100644 index 0000000..f8d66ed --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c55c112575869ddb19fb7232e8e481e6d5c433f0e318a463794fd5f1d31e52 +size 668787584 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf new file mode 100644 index 0000000..5ed035b --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a850602f42f524fa705fd08d1375ac3b01cfbd669834f9c290df30af772acb +size 783016832 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf new file mode 100644 index 0000000..e6de3df --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e63253540d2cf0d8efc9a8c0cb87f16df642f2f6add101ab38d61795b1eea9d +size 904385408 diff --git a/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf new file mode 100644 index 0000000..0c8929b --- /dev/null +++ b/tinyllama-1.1b-2t-lr-2e-4-3ep-dolly-15k-instruct-v1.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c0bfcfe74b1d983d24441f535e015869ce32e249afde258f5e52e7fa0a963e +size 1170781056