commit 2533d15397425c8c0f675135103fe64465c56221 Author: ModelHub XC Date: Thu Jun 18 14:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3b-Code-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..08aad1d --- /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 +Llama-3b-Code-Reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3b-Code-Reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3b-Code-Reasoning.IQ4_XS.gguf b/Llama-3b-Code-Reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..7df939a --- /dev/null +++ b/Llama-3b-Code-Reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85178de011abfb4edc06a7e4fc436b330450ac0108ffc3a918466ed8e9de5856 +size 1840906720 diff --git a/Llama-3b-Code-Reasoning.Q2_K.gguf b/Llama-3b-Code-Reasoning.Q2_K.gguf new file mode 100644 index 0000000..662f098 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b22885cbb8ef7698238022d1509629d42e48eb80cdfbdb9e5cad5a2928f217d +size 1363935712 diff --git a/Llama-3b-Code-Reasoning.Q3_K_L.gguf b/Llama-3b-Code-Reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..d779304 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8b32b68410d3757ab20c69192475325a868a96aa76927b75672b40c0e4a2308 +size 1815347680 diff --git a/Llama-3b-Code-Reasoning.Q3_K_M.gguf b/Llama-3b-Code-Reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..0942426 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbeedb7d7732e5940542c7e38a3fc400908da2a8ab4b401c95972e95fbec974 +size 1687159264 diff --git a/Llama-3b-Code-Reasoning.Q3_K_S.gguf b/Llama-3b-Code-Reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..920788f --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74676976206bf84dba6a366789f552753419acb59ab49e11ab484308313a2dc4 +size 1542848992 diff --git a/Llama-3b-Code-Reasoning.Q4_K_M.gguf b/Llama-3b-Code-Reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..600d663 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3e02cbf554d825c992fddfc5c752234082936032a37882b88087f3f00000276 +size 2019377632 diff --git a/Llama-3b-Code-Reasoning.Q4_K_S.gguf b/Llama-3b-Code-Reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..3fa9380 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c062e52a9fcadcaa5abfecbcc2aea9d770b76c90d5696a8c36e121f78e4005d +size 1928200672 diff --git a/Llama-3b-Code-Reasoning.Q5_K_M.gguf b/Llama-3b-Code-Reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..880b8c9 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261b398993990178f5cccb67ed078534d2849c09f91dec3a8d7ae18f2cf5a933 +size 2322153952 diff --git a/Llama-3b-Code-Reasoning.Q5_K_S.gguf b/Llama-3b-Code-Reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..2cab30e --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046c6c77e4840548c33bcde13271a197bc5e622b2e9ce0319c8163fba6223110 +size 2269512160 diff --git a/Llama-3b-Code-Reasoning.Q6_K.gguf b/Llama-3b-Code-Reasoning.Q6_K.gguf new file mode 100644 index 0000000..cb93ef4 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab0ba956aa6afb46bf9f0e948d59b6170789129c02d4da330021eabd9dab7a71 +size 2643853792 diff --git a/Llama-3b-Code-Reasoning.Q8_0.gguf b/Llama-3b-Code-Reasoning.Q8_0.gguf new file mode 100644 index 0000000..14118e9 --- /dev/null +++ b/Llama-3b-Code-Reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de620675baf33b7aa0f7763c50577f3f752d3a693136f435175d0a5d77cf1a82 +size 3421899232 diff --git a/Llama-3b-Code-Reasoning.f16.gguf b/Llama-3b-Code-Reasoning.f16.gguf new file mode 100644 index 0000000..27fee6f --- /dev/null +++ b/Llama-3b-Code-Reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa4bcf5d2275936af333ae96293659a7a271737c5e7e7ce4c271c4411b115bc +size 6433688032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b407a92 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: AdithyaSK/Llama-3b-Code-Reasoning +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/AdithyaSK/Llama-3b-Code-Reasoning + + +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/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3b-Code-Reasoning-GGUF/resolve/main/Llama-3b-Code-Reasoning.f16.gguf) | f16 | 6.5 | 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. + +