commit f9c3e429b8845d40cf51a5922bb16b93d8643c7b Author: ModelHub XC Date: Tue Apr 21 23:54:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: s3nh/TinyDolphin-2.8-1.1b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d7435b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +tinydolphin-2.8-1.1b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +tinydolphin-2.8-1.1b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinydolphin-2.8-1.1b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +tinydolphin-2.8-1.1b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +tinydolphin-2.8-1.1b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6294fe3 --- /dev/null +++ b/README.md @@ -0,0 +1,47 @@ + +--- +license: openrail +pipeline_tag: text-generation +library_name: transformers +language: +- zh +- en +--- + + +## Original model card + +Buy me a coffee if you like this project ;) + + +#### Description + +GGUF Format model files for [This project](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b). + +### GGUF Specs + +GGUF is a format based on the existing GGJT, but makes a few changes to the format to make it more extensible and easier to use. The following features are desired: + +Single-file deployment: they can be easily distributed and loaded, and do not require any external files for additional information. +Extensible: new features can be added to GGML-based executors/new information can be added to GGUF models without breaking compatibility with existing models. +mmap compatibility: models can be loaded using mmap for fast loading and saving. +Easy to use: models can be easily loaded and saved using a small amount of code, with no need for external libraries, regardless of the language used. +Full information: all information needed to load a model is contained in the model file, and no additional information needs to be provided by the user. +The key difference between GGJT and GGUF is the use of a key-value structure for the hyperparameters (now referred to as metadata), rather than a list of untyped values. +This allows for new metadata to be added without breaking compatibility with existing models, and to annotate the model with additional information that may be useful for +inference or for identifying the model. + + + +### inference + + + User: Tell me story about what is an quantization and what do we need to build. +- [ ] Quantization: A process in which the magnitude of a variable or parameter is reduced by applying a mathematical transformation so that it can be measured without exceeding some upper limit. +- [ ] What do we need to build? + - An algorithm (program) for quantizing data. + - Hardware and software resources (like GPUs, TPUs, etc.) to implement the algorithm. + - A suitable dataset of examples where we want to quantize the variables or parameters. + - Some kind of loss function, such as cross-entropy, which will measure how well our quant + +# Original model card diff --git a/tinydolphin-2.8-1.1b.Q3_K_S.gguf b/tinydolphin-2.8-1.1b.Q3_K_S.gguf new file mode 100644 index 0000000..f3ff1ae --- /dev/null +++ b/tinydolphin-2.8-1.1b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d281aa06a74702b1406a5ab47a430ea1f2d247a341003f4491db8888dcd8b5 +size 499347008 diff --git a/tinydolphin-2.8-1.1b.Q4_K_M.gguf b/tinydolphin-2.8-1.1b.Q4_K_M.gguf new file mode 100644 index 0000000..68a2ccf --- /dev/null +++ b/tinydolphin-2.8-1.1b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e72e3fb1387f5bdae0302d68d33d245dbcd1395d597170805a33b811b0e2bcb +size 667820128 diff --git a/tinydolphin-2.8-1.1b.Q5_K_M.gguf b/tinydolphin-2.8-1.1b.Q5_K_M.gguf new file mode 100644 index 0000000..53a8c58 --- /dev/null +++ b/tinydolphin-2.8-1.1b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeeec8dba4f64a2da63347588abd3b5ed97f96dd435dbf196c839bbeb1a937c7 +size 782049888 diff --git a/tinydolphin-2.8-1.1b.Q6_K.gguf b/tinydolphin-2.8-1.1b.Q6_K.gguf new file mode 100644 index 0000000..fdcf9bb --- /dev/null +++ b/tinydolphin-2.8-1.1b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf7c9012648ba5d24e4dc0b1f316d1d59dd5c09f405376a9e4250b2b3c1200f +size 903419008 diff --git a/tinydolphin-2.8-1.1b.Q8_0.gguf b/tinydolphin-2.8-1.1b.Q8_0.gguf new file mode 100644 index 0000000..8de728d --- /dev/null +++ b/tinydolphin-2.8-1.1b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412f9f68104b1e80948cb4a050ac12b1e3346b372ea42501b1291b1a39e0f166 +size 1169816640 diff --git a/tinydolphin-2.8-1.1b.fp16.bin b/tinydolphin-2.8-1.1b.fp16.bin new file mode 100644 index 0000000..55b43b4 --- /dev/null +++ b/tinydolphin-2.8-1.1b.fp16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3790ab4d7866a31f926eb7f98a54039fbd09bf3797de94099005828656e9f57e +size 2201033216