commit 26d9e22ad0490ea6783fffcfd6e6079d4b840dc6 Author: ModelHub XC Date: Thu Oct 22 10:10:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-FantasySciFi-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58e454d --- /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 +Llama3.2-1B-FantasySciFi.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-FantasySciFi.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-FantasySciFi.IQ4_XS.gguf b/Llama3.2-1B-FantasySciFi.IQ4_XS.gguf new file mode 100644 index 0000000..6d6549d --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48083cb0e85442df2068eb3ef34fab2f8a49946ce71268c76b0e6f9876726f7f +size 748385120 diff --git a/Llama3.2-1B-FantasySciFi.Q2_K.gguf b/Llama3.2-1B-FantasySciFi.Q2_K.gguf new file mode 100644 index 0000000..6232b01 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1af52db1b8568ddf84795059c74a7d3a2af32b8dc08bc157362fb71b12c65c4 +size 580875104 diff --git a/Llama3.2-1B-FantasySciFi.Q3_K_L.gguf b/Llama3.2-1B-FantasySciFi.Q3_K_L.gguf new file mode 100644 index 0000000..f0f9517 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a01a25d8daa982ca1717df18c1a2773ce7651ca1df7648539dfe8998f6147e51 +size 732525408 diff --git a/Llama3.2-1B-FantasySciFi.Q3_K_M.gguf b/Llama3.2-1B-FantasySciFi.Q3_K_M.gguf new file mode 100644 index 0000000..d15bf78 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f65fc205307a465873d814b761e794c3862e2457e68f96d5e7c403a96d968a9 +size 690844512 diff --git a/Llama3.2-1B-FantasySciFi.Q3_K_S.gguf b/Llama3.2-1B-FantasySciFi.Q3_K_S.gguf new file mode 100644 index 0000000..e763106 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04541ee6d7f5c9d9d695946e45af27e51f0e7c1d6a2a6cc01d3833a8aacc2a9 +size 641692512 diff --git a/Llama3.2-1B-FantasySciFi.Q4_K_M.gguf b/Llama3.2-1B-FantasySciFi.Q4_K_M.gguf new file mode 100644 index 0000000..f03e232 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1026bd16a420baf696639d9bee8e123c56caf5c4828f4f1f440083744b6ac2a +size 807695200 diff --git a/Llama3.2-1B-FantasySciFi.Q4_K_S.gguf b/Llama3.2-1B-FantasySciFi.Q4_K_S.gguf new file mode 100644 index 0000000..636e0c8 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042cfbbab4d4745ced49c0b3aa05ca868f0d0b8d2b233ed7d31ebe7afa2812dc +size 775648096 diff --git a/Llama3.2-1B-FantasySciFi.Q5_K_M.gguf b/Llama3.2-1B-FantasySciFi.Q5_K_M.gguf new file mode 100644 index 0000000..16ba8b3 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d2b8a0143805a90fbe8c3f2bea366ed14c3c6e2f4dc82f9f99880938da5841 +size 911504224 diff --git a/Llama3.2-1B-FantasySciFi.Q5_K_S.gguf b/Llama3.2-1B-FantasySciFi.Q5_K_S.gguf new file mode 100644 index 0000000..3f5184e --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b00c5419d5837515e208ee6bc0e7c46bec84199abdb9ecc2aa08c33f8eaebc2 +size 892564320 diff --git a/Llama3.2-1B-FantasySciFi.Q6_K.gguf b/Llama3.2-1B-FantasySciFi.Q6_K.gguf new file mode 100644 index 0000000..2be1586 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba1502116088fbadedc32a5c4fc63b477cce4d06a3433e96e8f95dd2bcd2f7e +size 1021801312 diff --git a/Llama3.2-1B-FantasySciFi.Q8_0.gguf b/Llama3.2-1B-FantasySciFi.Q8_0.gguf new file mode 100644 index 0000000..2e76bc6 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6e41781cfdb8a2a65e26e74f4834a5662e6c32cfce14b0ac14c683a7235a66 +size 1321083744 diff --git a/Llama3.2-1B-FantasySciFi.f16.gguf b/Llama3.2-1B-FantasySciFi.f16.gguf new file mode 100644 index 0000000..fde3047 --- /dev/null +++ b/Llama3.2-1B-FantasySciFi.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a260b4cd04e20574f9049c9f68fc194c639abc3dd4fdcbe4825e51a2cbe545 +size 2479596384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e95507 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: theprint/Llama3.2-1B-FantasySciFi +datasets: +- theprint/SciFi-Fantasy-alpaca +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/Llama3.2-1B-FantasySciFi + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-1B-FantasySciFi-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-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/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-FantasySciFi-GGUF/resolve/main/Llama3.2-1B-FantasySciFi.f16.gguf) | f16 | 2.6 | 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. + +