commit 9f518e5e9ae540e688c1660772aa9a55ae3f9f3e Author: ModelHub XC Date: Thu Jun 25 03:10:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c28fa36 --- /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 +Base-Roblox-coder-Llama-3.2-3B-vLLM.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Base-Roblox-coder-Llama-3.2-3B-vLLM.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.IQ4_XS.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.IQ4_XS.gguf new file mode 100644 index 0000000..d30e5a4 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddae4ec3c604bb127142381df4eb2ac828a50c44de5a53d29c781506f0a37d0d +size 1840908128 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q2_K.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q2_K.gguf new file mode 100644 index 0000000..16c7677 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc758e29ed719a5bcc2bc50ce390022542a944a1dbc5ed5418f069808d52a9af +size 1363937120 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_L.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_L.gguf new file mode 100644 index 0000000..f1bf9e3 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3cf6d953bf261f5848e1e881bf985f03b45a419790ad6b98d84a1f2f7b90bb +size 1815349088 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_M.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_M.gguf new file mode 100644 index 0000000..1f3b2f1 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfb3323d39a1a4d616176e77620edd2e9dba337a5564b566bfe2f3dfe09cf6a +size 1687160672 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_S.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_S.gguf new file mode 100644 index 0000000..a7cf66f --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc54ed4f6c18cd0450bdeb4da90af255f1ac7f6447138af9df8915e9f24de50 +size 1542850400 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_M.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_M.gguf new file mode 100644 index 0000000..1ede77d --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d39570200b16282de6b86c055ede31603cc82f9bf50d2552ebfcf5bbec1fb1 +size 2019379040 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_S.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_S.gguf new file mode 100644 index 0000000..f67425a --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d188f3f88f7968d87faea7db2d15a82b4d6f21a590458e1250274aa3ef7267 +size 1928202080 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_M.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_M.gguf new file mode 100644 index 0000000..ed15609 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f24d087ab31f5dd9d40ce408b3c7c0966d0401cde62ee6441033ddec3b4f357 +size 2322155360 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_S.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_S.gguf new file mode 100644 index 0000000..72e6e5a --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07143ee280228bb5d100df57129d08f9a6347ad155d7056152d111be5eb8a23f +size 2269513568 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q6_K.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q6_K.gguf new file mode 100644 index 0000000..e1f740f --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b8a9f684776d8464ee7aeda72fb5c4819928346e05e0c80b82f27a82deaded +size 2643855200 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q8_0.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q8_0.gguf new file mode 100644 index 0000000..6b26403 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a858a959b588eeeb57dc6cf9d5d0336f8c725178c96fd2d1235e7ba7c0597e4 +size 3421900640 diff --git a/Base-Roblox-coder-Llama-3.2-3B-vLLM.f16.gguf b/Base-Roblox-coder-Llama-3.2-3B-vLLM.f16.gguf new file mode 100644 index 0000000..0d87fe5 --- /dev/null +++ b/Base-Roblox-coder-Llama-3.2-3B-vLLM.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72d1a1b98e527e8a3d2d956ba8d21e30f9b511eeef3c4f3d5db50890c2582c6 +size 6433689440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4aa70be --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Pinkstack/Base-Roblox-coder-Llama-3.2-3B-vLLM +datasets: +- Roblox/luau_corpus +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- luau +- code +--- +## About + + + + + + +static quants of https://huggingface.co/Pinkstack/Base-Roblox-coder-Llama-3.2-3B-vLLM + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Base-Roblox-coder-Llama-3.2-3B-vLLM-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/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Base-Roblox-coder-Llama-3.2-3B-vLLM-GGUF/resolve/main/Base-Roblox-coder-Llama-3.2-3B-vLLM.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. + +