commit 39cd9b7fe01ce350bc61d0530aae880ad3fbcc52 Author: ModelHub XC Date: Wed Apr 29 11:26:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TinyLlama-1.1B_fictional_v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1850808 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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_fictional_v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TinyLlama-1.1B_fictional_v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0bb26cd --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: yzhuang/TinyLlama-1.1B_fictional_v2 +datasets: +- generator +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- trl +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/yzhuang/TinyLlama-1.1B_fictional_v2 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B_fictional_v2-GGUF/resolve/main/TinyLlama-1.1B_fictional_v2.f16.gguf) | f16 | 2.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/TinyLlama-1.1B_fictional_v2.IQ4_XS.gguf b/TinyLlama-1.1B_fictional_v2.IQ4_XS.gguf new file mode 100644 index 0000000..d3411d9 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff37481868ab9fbeb2a8e3b1334312e507096f4bb02bf08cccf01b663d5a878 +size 609808768 diff --git a/TinyLlama-1.1B_fictional_v2.Q2_K.gguf b/TinyLlama-1.1B_fictional_v2.Q2_K.gguf new file mode 100644 index 0000000..de408d2 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41eb8bc96c16921239812c4c11c8a752db987f0c0ce1fd8ab225c306e9febdf8 +size 432132480 diff --git a/TinyLlama-1.1B_fictional_v2.Q3_K_L.gguf b/TinyLlama-1.1B_fictional_v2.Q3_K_L.gguf new file mode 100644 index 0000000..1877e11 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c42b8eddf84ef3f01e66eee18e07b39e85e7b8b6fef3bece4ab426dbd563490 +size 591528320 diff --git a/TinyLlama-1.1B_fictional_v2.Q3_K_M.gguf b/TinyLlama-1.1B_fictional_v2.Q3_K_M.gguf new file mode 100644 index 0000000..7a92670 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b727f7bf58675eeb72225ca8ac922faa6a09533cec9239ce8d54cf3829fe3e6 +size 548405632 diff --git a/TinyLlama-1.1B_fictional_v2.Q3_K_S.gguf b/TinyLlama-1.1B_fictional_v2.Q3_K_S.gguf new file mode 100644 index 0000000..0393f0b --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f96a8670a63c44f4eec719a330ec0ca165cfa1958522aa4547061ed631d5ff2 +size 499343744 diff --git a/TinyLlama-1.1B_fictional_v2.Q4_K_M.gguf b/TinyLlama-1.1B_fictional_v2.Q4_K_M.gguf new file mode 100644 index 0000000..4352133 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e343b9afb91997249af6297a98ae8622f4a1f5e8b4fbab3fd33aad8e2abb00f +size 667816320 diff --git a/TinyLlama-1.1B_fictional_v2.Q4_K_S.gguf b/TinyLlama-1.1B_fictional_v2.Q4_K_S.gguf new file mode 100644 index 0000000..ca118a9 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5b1ae50bf108ddd13d1e17d7809666fd3941ffa3a159ee5e3434a927bf70d6 +size 639873408 diff --git a/TinyLlama-1.1B_fictional_v2.Q5_K_M.gguf b/TinyLlama-1.1B_fictional_v2.Q5_K_M.gguf new file mode 100644 index 0000000..19b0f6f --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babf8e91b4cf5a7b32ac0af9758151c3845a6ee36f43d3e0de8373d3abfd01f2 +size 782045568 diff --git a/TinyLlama-1.1B_fictional_v2.Q5_K_S.gguf b/TinyLlama-1.1B_fictional_v2.Q5_K_S.gguf new file mode 100644 index 0000000..89a9f6c --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa35e696e8b249df1a15bd3f12f9c1fb01beca14075863224df77d63fc7bc317 +size 766030208 diff --git a/TinyLlama-1.1B_fictional_v2.Q6_K.gguf b/TinyLlama-1.1B_fictional_v2.Q6_K.gguf new file mode 100644 index 0000000..b30beb9 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d4b4437d54f74195ffed06f5f2bc3c1babcbc7d8fad94f2da79ce5d05dc764 +size 903414144 diff --git a/TinyLlama-1.1B_fictional_v2.Q8_0.gguf b/TinyLlama-1.1B_fictional_v2.Q8_0.gguf new file mode 100644 index 0000000..099c583 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e3f9d9f576024712ef614a7ce4c5b58f48ed0f629c844f2c3fcbd21baea8b5 +size 1169809792 diff --git a/TinyLlama-1.1B_fictional_v2.f16.gguf b/TinyLlama-1.1B_fictional_v2.f16.gguf new file mode 100644 index 0000000..d2fc157 --- /dev/null +++ b/TinyLlama-1.1B_fictional_v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddac2bb961320fe77025f8b8474e6340711a59f31c7473040c52e551cd4d8988 +size 2201018752