commit 8e42b4fa1111f511bb2aaeea2e3d9d0de4cee750 Author: ModelHub XC Date: Wed May 27 11:36:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llamatron-1B-peft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..23e9bd8 --- /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 +llamatron-1B-peft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llamatron-1B-peft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ddd2f69 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: suwesh/llamatron-1B-peft +datasets: +- nvidia/Llama-Nemotron-Post-Training-Dataset +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- peft +- chat +- LoRA +- RTX3060 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/suwesh/llamatron-1B-peft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llamatron-1B-peft-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/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llamatron-1B-peft-GGUF/resolve/main/llamatron-1B-peft.f16.gguf) | f16 | 3.1 | 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. + + diff --git a/llamatron-1B-peft.IQ4_XS.gguf b/llamatron-1B-peft.IQ4_XS.gguf new file mode 100644 index 0000000..43eb615 --- /dev/null +++ b/llamatron-1B-peft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c000a84ab77108c7e2c1597b9041d544c241eb347dff04ad4229317ed093aaf +size 887927680 diff --git a/llamatron-1B-peft.Q2_K.gguf b/llamatron-1B-peft.Q2_K.gguf new file mode 100644 index 0000000..200ae9f --- /dev/null +++ b/llamatron-1B-peft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122b135829b8abe944db2240b84d57a04ea047ad233f15c29a06cf2978a74930 +size 667063168 diff --git a/llamatron-1B-peft.Q3_K_L.gguf b/llamatron-1B-peft.Q3_K_L.gguf new file mode 100644 index 0000000..ff56187 --- /dev/null +++ b/llamatron-1B-peft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c6b6726bf64242036868ca6b2abdbb5f7ad869fd25672fa67d8ae2a6ecb5b9 +size 845390720 diff --git a/llamatron-1B-peft.Q3_K_M.gguf b/llamatron-1B-peft.Q3_K_M.gguf new file mode 100644 index 0000000..bb3a160 --- /dev/null +++ b/llamatron-1B-peft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07c9e9fcef6772895fd7eed8fe17e79fb267baa6f8dc11dcc7f13f7591be989 +size 803709824 diff --git a/llamatron-1B-peft.Q3_K_S.gguf b/llamatron-1B-peft.Q3_K_S.gguf new file mode 100644 index 0000000..6cf965b --- /dev/null +++ b/llamatron-1B-peft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597acb1bf2210d9139959469cfff142398ef3fcee58a88901c9c2ac78aa9f227 +size 754557824 diff --git a/llamatron-1B-peft.Q4_K_M.gguf b/llamatron-1B-peft.Q4_K_M.gguf new file mode 100644 index 0000000..0e66a60 --- /dev/null +++ b/llamatron-1B-peft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3a12e3e87bd5dad0ddb724f144975f3a53801491b602a4d690047809d6a2c0 +size 955446144 diff --git a/llamatron-1B-peft.Q4_K_S.gguf b/llamatron-1B-peft.Q4_K_S.gguf new file mode 100644 index 0000000..8da0f68 --- /dev/null +++ b/llamatron-1B-peft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a27da5ea3e113ac21e55ef653cda0f2d312f2b0d37cfbe5d4e81f6085b36328 +size 923399040 diff --git a/llamatron-1B-peft.Q5_K_M.gguf b/llamatron-1B-peft.Q5_K_M.gguf new file mode 100644 index 0000000..b3bb316 --- /dev/null +++ b/llamatron-1B-peft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62deccdf7007186a4d7b2947d5236b6474f3f09672b90be6fb9037d8d43100b5 +size 1092088704 diff --git a/llamatron-1B-peft.Q5_K_S.gguf b/llamatron-1B-peft.Q5_K_S.gguf new file mode 100644 index 0000000..d71d3dd --- /dev/null +++ b/llamatron-1B-peft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879e7c169ebb47dfb01faec3032a1d8ae69a2f5c22788c7bf6ebbc6976d2a5b7 +size 1073148800 diff --git a/llamatron-1B-peft.Q6_K.gguf b/llamatron-1B-peft.Q6_K.gguf new file mode 100644 index 0000000..8a01cc0 --- /dev/null +++ b/llamatron-1B-peft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc10824bdf1c59215551cfd2b85a1c43f31697727f83391d1f8ab53856e7d803 +size 1237271424 diff --git a/llamatron-1B-peft.Q8_0.gguf b/llamatron-1B-peft.Q8_0.gguf new file mode 100644 index 0000000..fa39bec --- /dev/null +++ b/llamatron-1B-peft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b540d9559deaf783790c3d434ea92bf447419b09f1148ab19fcfc34a6376e58 +size 1600168832 diff --git a/llamatron-1B-peft.f16.gguf b/llamatron-1B-peft.f16.gguf new file mode 100644 index 0000000..e2f7078 --- /dev/null +++ b/llamatron-1B-peft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b794afcb9871dc2bdc0e4c4742f4bc6b1028511705ca44253810f4251b180666 +size 3004932992