commit 74aa5afa082c519349ede6acdc2250f282f5ee5f Author: ModelHub XC Date: Sun Jun 21 08:27:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/IBM-GPT5.4-Coder-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8dc7fd6 --- /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 +IBM-GPT5.4-Coder-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT5.4-Coder-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/IBM-GPT5.4-Coder-1B.IQ4_XS.gguf b/IBM-GPT5.4-Coder-1B.IQ4_XS.gguf new file mode 100644 index 0000000..4fef2c9 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34f9e116c1f813bf7be1023da43a14be75c414244fe9ac66da34237249bd928 +size 943529024 diff --git a/IBM-GPT5.4-Coder-1B.Q2_K.gguf b/IBM-GPT5.4-Coder-1B.Q2_K.gguf new file mode 100644 index 0000000..9198580 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca38f28ab2059c5b8597ca7bb52007fd0316283ae8917fc36547ddded0f763a +size 701701184 diff --git a/IBM-GPT5.4-Coder-1B.Q3_K_L.gguf b/IBM-GPT5.4-Coder-1B.Q3_K_L.gguf new file mode 100644 index 0000000..21e48e5 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e098baa5f9559d85cffd1435935f97500ee4db39808032c99a8fae0e120e2465 +size 926161984 diff --git a/IBM-GPT5.4-Coder-1B.Q3_K_M.gguf b/IBM-GPT5.4-Coder-1B.Q3_K_M.gguf new file mode 100644 index 0000000..ee79922 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d7353dcce7dc7be59ff32d0185d746a707c4dc8d1adff126e6249c834019bc +size 860363840 diff --git a/IBM-GPT5.4-Coder-1B.Q3_K_S.gguf b/IBM-GPT5.4-Coder-1B.Q3_K_S.gguf new file mode 100644 index 0000000..1c8f713 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4db0f131f47b3a3f2b8fadbd8b0b893e2d56537cdd59beec20368f4896ba34 +size 785587264 diff --git a/IBM-GPT5.4-Coder-1B.Q4_K_M.gguf b/IBM-GPT5.4-Coder-1B.Q4_K_M.gguf new file mode 100644 index 0000000..45ba58d --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db70f3511f658504b0280f4e9bb9afa0075d466e3d73da7a09bd7fafefb141d8 +size 1023646784 diff --git a/IBM-GPT5.4-Coder-1B.Q4_K_S.gguf b/IBM-GPT5.4-Coder-1B.Q4_K_S.gguf new file mode 100644 index 0000000..bdbbf2f --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a849e3bc0140a0d705acb81ffbc42a03c3fb92d9234faa6a7674b2673d135a45 +size 980753472 diff --git a/IBM-GPT5.4-Coder-1B.Q5_K_M.gguf b/IBM-GPT5.4-Coder-1B.Q5_K_M.gguf new file mode 100644 index 0000000..000c02e --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4f64417b2a8d54eb049d6155e8a8fa66e39b7a5baa5c0fa38ae8e58d403134 +size 1178311744 diff --git a/IBM-GPT5.4-Coder-1B.Q5_K_S.gguf b/IBM-GPT5.4-Coder-1B.Q5_K_S.gguf new file mode 100644 index 0000000..fdf8bce --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6708d3b8284cc1fc912b6334ff86af01c6e1f98b534cf03a8c361b151e4c2613 +size 1153244224 diff --git a/IBM-GPT5.4-Coder-1B.Q6_K.gguf b/IBM-GPT5.4-Coder-1B.Q6_K.gguf new file mode 100644 index 0000000..c67a175 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103956e08232dafeff7faecacaf9a856f4701455439324957f69248ed7da9657 +size 1342643264 diff --git a/IBM-GPT5.4-Coder-1B.Q8_0.gguf b/IBM-GPT5.4-Coder-1B.Q8_0.gguf new file mode 100644 index 0000000..a93fe07 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4f3d17f5361774ae5b2029d7f0dd8cbde87534788a5e40fcba5e006f16ebd6 +size 1737792576 diff --git a/IBM-GPT5.4-Coder-1B.f16.gguf b/IBM-GPT5.4-Coder-1B.f16.gguf new file mode 100644 index 0000000..b646947 --- /dev/null +++ b/IBM-GPT5.4-Coder-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bede1e180a4e3e9910db84d5b77ed75ade064a81276a6fbb1229d79110d00c27 +size 3267402816 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae8a61b --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Oxy29/IBM-GPT5.4-Coder-1B +datasets: +- Roman1111111/gpt-5.4-step-by-step-reasoning +- TeichAI/gpt-5.1-codex-max-1000x +- TeichAI/gpt-5.1-high-reasoning-1000x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- granite +- ibm +- full-finetune +- dual-gpu +- code +- reasoning +- text-generation +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Oxy29/IBM-GPT5.4-Coder-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#IBM-GPT5.4-Coder-1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-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/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT5.4-Coder-1B-GGUF/resolve/main/IBM-GPT5.4-Coder-1B.f16.gguf) | f16 | 3.4 | 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. + +