commit ce0f4001e22449c8b0f995f8d302eeff7643e04a Author: ModelHub XC Date: Tue Sep 1 00:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mellum-4b-sft-rust-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81512d8 --- /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 +Mellum-4b-sft-rust.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mellum-4b-sft-rust.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mellum-4b-sft-rust.IQ4_XS.gguf b/Mellum-4b-sft-rust.IQ4_XS.gguf new file mode 100644 index 0000000..4c024fb --- /dev/null +++ b/Mellum-4b-sft-rust.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98330f23e4f9144d37cea46df3443055fae66691b5100d5626fcae55c94e3b8 +size 2264732416 diff --git a/Mellum-4b-sft-rust.Q2_K.gguf b/Mellum-4b-sft-rust.Q2_K.gguf new file mode 100644 index 0000000..02b1f12 --- /dev/null +++ b/Mellum-4b-sft-rust.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5112a2019723bda77ac7f90bb2d82bfd774ccb6e23c76b8902a52217d5193a9a +size 1707496192 diff --git a/Mellum-4b-sft-rust.Q3_K_L.gguf b/Mellum-4b-sft-rust.Q3_K_L.gguf new file mode 100644 index 0000000..de47878 --- /dev/null +++ b/Mellum-4b-sft-rust.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8914437ab2903e641fe325c447e4fd0509a9b77128898aac8daf3c9b77976708 +size 2238872320 diff --git a/Mellum-4b-sft-rust.Q3_K_M.gguf b/Mellum-4b-sft-rust.Q3_K_M.gguf new file mode 100644 index 0000000..0602c6c --- /dev/null +++ b/Mellum-4b-sft-rust.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37813ba9a7d5ebfbc5e5761e6a096225da4f509556a31f8df05437b05d27f46 +size 2124483328 diff --git a/Mellum-4b-sft-rust.Q3_K_S.gguf b/Mellum-4b-sft-rust.Q3_K_S.gguf new file mode 100644 index 0000000..51166f6 --- /dev/null +++ b/Mellum-4b-sft-rust.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3a4d84296a39b0e56c41574335208e812170eae6385c0dbabee14ca11c07df2 +size 1950227200 diff --git a/Mellum-4b-sft-rust.Q4_K_M.gguf b/Mellum-4b-sft-rust.Q4_K_M.gguf new file mode 100644 index 0000000..643a991 --- /dev/null +++ b/Mellum-4b-sft-rust.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a1a9813a35c40acf0ca7945cc7105f84a1110f5303652f1b547af3c8d2d6e5 +size 2605171456 diff --git a/Mellum-4b-sft-rust.Q4_K_S.gguf b/Mellum-4b-sft-rust.Q4_K_S.gguf new file mode 100644 index 0000000..86c088d --- /dev/null +++ b/Mellum-4b-sft-rust.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238c2866b361057b78a50730489f3e7b2bbfe5356646f6e960079d92d288cd02 +size 2447430400 diff --git a/Mellum-4b-sft-rust.Q5_K_M.gguf b/Mellum-4b-sft-rust.Q5_K_M.gguf new file mode 100644 index 0000000..7cdd0c2 --- /dev/null +++ b/Mellum-4b-sft-rust.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21c9d70d67bc3102b37f60c6b0f8a57e78736e2d7f908fb844da06161a2f8b4 +size 2983543552 diff --git a/Mellum-4b-sft-rust.Q5_K_S.gguf b/Mellum-4b-sft-rust.Q5_K_S.gguf new file mode 100644 index 0000000..213e24d --- /dev/null +++ b/Mellum-4b-sft-rust.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca0b5b5b11fbfd5039a5b7f7f89c567486ad7f25370de51bcf35a1e77e1eac5 +size 2855035648 diff --git a/Mellum-4b-sft-rust.Q6_K.gguf b/Mellum-4b-sft-rust.Q6_K.gguf new file mode 100644 index 0000000..a32be05 --- /dev/null +++ b/Mellum-4b-sft-rust.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6e8fdabce5bfb8a4aa3ad918b2b29e1d8840a469dafc4825a90483db9ec6e2 +size 3485428480 diff --git a/Mellum-4b-sft-rust.Q8_0.gguf b/Mellum-4b-sft-rust.Q8_0.gguf new file mode 100644 index 0000000..67a9580 --- /dev/null +++ b/Mellum-4b-sft-rust.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe366f08a4ef2514959b3940139a7bd823d2f055910200d6a2053f50a304541e +size 4274520832 diff --git a/Mellum-4b-sft-rust.f16.gguf b/Mellum-4b-sft-rust.f16.gguf new file mode 100644 index 0000000..3126281 --- /dev/null +++ b/Mellum-4b-sft-rust.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba854c215c662bb4f0a1ee844166e1a586f6e4cc2b84976a65cd8b4f458f8e5a +size 8042390272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c69825 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: Etherll/Mellum-4b-sft-rust +datasets: +- Etherll/CodeFIM-Rust-Mellum +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- code +- rust +- fill-in-the-middle +- fim +- text-generation +- llm +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Etherll/Mellum-4b-sft-rust + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mellum-4b-sft-rust-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Mellum-4b-sft-rust-i1-GGUF +## 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/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q3_K_S.gguf) | Q3_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q4_K_M.gguf) | Q4_K_M | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q5_K_S.gguf) | Q5_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q5_K_M.gguf) | Q5_K_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q6_K.gguf) | Q6_K | 3.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mellum-4b-sft-rust-GGUF/resolve/main/Mellum-4b-sft-rust.f16.gguf) | f16 | 8.1 | 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. + +