commit 2db675742512762d9a93805146eb3c41451aff42 Author: ModelHub XC Date: Fri Jun 26 06:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1b4c970 --- /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 +Gamma-Velorum-1.5B-Thinker.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gamma-Velorum-1.5B-Thinker.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gamma-Velorum-1.5B-Thinker.IQ4_XS.gguf b/Gamma-Velorum-1.5B-Thinker.IQ4_XS.gguf new file mode 100644 index 0000000..990cab0 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f58127d77ba2869ef492edae1944ce5a6739e7003d320df2cc0c863fdb6451 +size 902183360 diff --git a/Gamma-Velorum-1.5B-Thinker.Q2_K.gguf b/Gamma-Velorum-1.5B-Thinker.Q2_K.gguf new file mode 100644 index 0000000..d99f886 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8582852b0a15d1d2398fe61a0765389633aa5d0c688b0bf75a355d8940d66031 +size 676305344 diff --git a/Gamma-Velorum-1.5B-Thinker.Q3_K_L.gguf b/Gamma-Velorum-1.5B-Thinker.Q3_K_L.gguf new file mode 100644 index 0000000..70517a9 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb5a5344d9263a5d70e011674d8a725828a3856a300dc382d14ce9ce5a0bb7a +size 880163264 diff --git a/Gamma-Velorum-1.5B-Thinker.Q3_K_M.gguf b/Gamma-Velorum-1.5B-Thinker.Q3_K_M.gguf new file mode 100644 index 0000000..58fe040 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13195456188ca6f252f909aeb6f4910e28fd3d4ebda7722eee19bddc43fcd6f +size 824179136 diff --git a/Gamma-Velorum-1.5B-Thinker.Q3_K_S.gguf b/Gamma-Velorum-1.5B-Thinker.Q3_K_S.gguf new file mode 100644 index 0000000..d77e3ef --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54da232401b0d4d59687f14dcc7a3446636ac083729b22c0c1aae2f5f191499d +size 760945088 diff --git a/Gamma-Velorum-1.5B-Thinker.Q4_K_M.gguf b/Gamma-Velorum-1.5B-Thinker.Q4_K_M.gguf new file mode 100644 index 0000000..709371d --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d7109325acccd05f39119f794037186653ca7c5a05a973ea467968b9251f3e +size 986048960 diff --git a/Gamma-Velorum-1.5B-Thinker.Q4_K_S.gguf b/Gamma-Velorum-1.5B-Thinker.Q4_K_S.gguf new file mode 100644 index 0000000..d2e5101 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8a6fe7689359313db682eddc64f95fccd9c1a3fdcbea88e0dc4e48c80d7550 +size 940313024 diff --git a/Gamma-Velorum-1.5B-Thinker.Q5_K_M.gguf b/Gamma-Velorum-1.5B-Thinker.Q5_K_M.gguf new file mode 100644 index 0000000..990c2e3 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6331f7402d8189880045ef2a70b46f16ff99e7c37fd9a08d549c6a86a276913f +size 1125050816 diff --git a/Gamma-Velorum-1.5B-Thinker.Q5_K_S.gguf b/Gamma-Velorum-1.5B-Thinker.Q5_K_S.gguf new file mode 100644 index 0000000..b4dc9b8 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff4f5d747c3f15a85ebad9e007a275aa405b2b2d28105eba5cede24b8ec7ade +size 1098729920 diff --git a/Gamma-Velorum-1.5B-Thinker.Q6_K.gguf b/Gamma-Velorum-1.5B-Thinker.Q6_K.gguf new file mode 100644 index 0000000..30d113a --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e70966b2510dd06ea0c77a2234c31d3b408e3046389078f8d0201ff831acc0c +size 1272740288 diff --git a/Gamma-Velorum-1.5B-Thinker.Q8_0.gguf b/Gamma-Velorum-1.5B-Thinker.Q8_0.gguf new file mode 100644 index 0000000..e5949d4 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24d16ae10ea014363b0acc4a7fe5a725423e0b4783526422c35c817affbbd97 +size 1646573504 diff --git a/Gamma-Velorum-1.5B-Thinker.f16.gguf b/Gamma-Velorum-1.5B-Thinker.f16.gguf new file mode 100644 index 0000000..f7a6195 --- /dev/null +++ b/Gamma-Velorum-1.5B-Thinker.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb84a7d109ce456fc251e15f11a33667a3309fbbf5d9baff866150e09be605d3 +size 3093669824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb64dc0 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: prithivMLmods/Gamma-Velorum-1.5B-Thinker +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- Math +- Code +- Thinker +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Gamma-Velorum-1.5B-Thinker + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gamma-Velorum-1.5B-Thinker-GGUF).*** + +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/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gamma-Velorum-1.5B-Thinker-GGUF/resolve/main/Gamma-Velorum-1.5B-Thinker.f16.gguf) | f16 | 3.2 | 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. + +