commit 47089b8a2f3b39243e6d269d5583ce83a9f6dce0 Author: ModelHub XC Date: Wed Jun 10 03:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/1.5B-v21-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c6eeac0 --- /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 +1.5B-v21.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +1.5B-v21.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/1.5B-v21.IQ4_XS.gguf b/1.5B-v21.IQ4_XS.gguf new file mode 100644 index 0000000..45474a2 --- /dev/null +++ b/1.5B-v21.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79dc1913f09af8c972cf68a00cab7c36d0b75b0d0e2990e023846d7a6a5f3233 +size 1181587616 diff --git a/1.5B-v21.Q2_K.gguf b/1.5B-v21.Q2_K.gguf new file mode 100644 index 0000000..1e0c0f5 --- /dev/null +++ b/1.5B-v21.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47d7831f72ca317aee3e2b4748931f08fd2fd654aea457f399e5837ce980d1af +size 879896736 diff --git a/1.5B-v21.Q3_K_L.gguf b/1.5B-v21.Q3_K_L.gguf new file mode 100644 index 0000000..291c1b4 --- /dev/null +++ b/1.5B-v21.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d981534b2a9368348595490c940b114b3dab849afe1d4447dafdfd0b51830e8 +size 1137205408 diff --git a/1.5B-v21.Q3_K_M.gguf b/1.5B-v21.Q3_K_M.gguf new file mode 100644 index 0000000..7632ec9 --- /dev/null +++ b/1.5B-v21.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35c826a2a069294488756f3932700ab2dda130e62c5eed7a5b4da346719891a2 +size 1073242272 diff --git a/1.5B-v21.Q3_K_S.gguf b/1.5B-v21.Q3_K_S.gguf new file mode 100644 index 0000000..f8f45f5 --- /dev/null +++ b/1.5B-v21.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea16d96378654afcf235638aacafd312cc34d8624c788f316a3c6b4e9efe247 +size 1000956064 diff --git a/1.5B-v21.Q4_K_M.gguf b/1.5B-v21.Q4_K_M.gguf new file mode 100644 index 0000000..6938086 --- /dev/null +++ b/1.5B-v21.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6310c116d2c0a7e5320cd47db80e059b828de7c09bcdb7ae9b0bf3f2d9f37c77 +size 1282439328 diff --git a/1.5B-v21.Q4_K_S.gguf b/1.5B-v21.Q4_K_S.gguf new file mode 100644 index 0000000..ed0c4fe --- /dev/null +++ b/1.5B-v21.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0a59d025af98e85e76e6644494d8e86bd1c176b88ef1f91c69feaacea7a600 +size 1235220640 diff --git a/1.5B-v21.Q5_K_M.gguf b/1.5B-v21.Q5_K_M.gguf new file mode 100644 index 0000000..47c2d5e --- /dev/null +++ b/1.5B-v21.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea42942cc5cc041291ecf8dfc9dabf82190b1933f619660b0191b0a0b81ee4f +size 1471805600 diff --git a/1.5B-v21.Q5_K_S.gguf b/1.5B-v21.Q5_K_S.gguf new file mode 100644 index 0000000..8ec32be --- /dev/null +++ b/1.5B-v21.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cf5bff09c7992c680e05a6a7ece8941f80fb9d606b4bb6582fde14ba4bdd3a +size 1444509856 diff --git a/1.5B-v21.Q6_K.gguf b/1.5B-v21.Q6_K.gguf new file mode 100644 index 0000000..47a05b1 --- /dev/null +++ b/1.5B-v21.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eead844c074fd68681e461cc81798f084c67cd6e151497e5e8bcc3e37ec0bfd +size 1673007264 diff --git a/1.5B-v21.Q8_0.gguf b/1.5B-v21.Q8_0.gguf new file mode 100644 index 0000000..821fd9c --- /dev/null +++ b/1.5B-v21.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b667db37696b6d32eb6d3782795e1b51115b96e276ed189e0e7565f4556a9956 +size 2165039264 diff --git a/1.5B-v21.f16.gguf b/1.5B-v21.f16.gguf new file mode 100644 index 0000000..bd54b85 --- /dev/null +++ b/1.5B-v21.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1f4e429b82d29986cc8311addd71a734254d9cf70ae5a310b1154f87e5e1524 +size 4069679264 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ebc6d5e --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ryzax/1.5B-v21 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ryzax/1.5B-v21 + + +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/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q2_K.gguf) | Q2_K | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q3_K_M.gguf) | Q3_K_M | 1.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.IQ4_XS.gguf) | IQ4_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q4_K_M.gguf) | Q4_K_M | 1.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q5_K_M.gguf) | Q5_K_M | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q6_K.gguf) | Q6_K | 1.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.Q8_0.gguf) | Q8_0 | 2.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/1.5B-v21-GGUF/resolve/main/1.5B-v21.f16.gguf) | f16 | 4.2 | 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. + +