commit 5ef36b6c10d828329daa3c4774e89c0855d1dc6b Author: ModelHub XC Date: Wed Oct 21 17:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3B-Enigma-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6688715 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama3.2-3B-Enigma.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-Enigma.IQ4_XS.gguf b/Llama3.2-3B-Enigma.IQ4_XS.gguf new file mode 100644 index 0000000..faa4114 --- /dev/null +++ b/Llama3.2-3B-Enigma.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f91ccd9ed5307e97e34950ca6903e56d4497ee1afb0af4f402b0598c6bbd76 +size 1840907936 diff --git a/Llama3.2-3B-Enigma.Q2_K.gguf b/Llama3.2-3B-Enigma.Q2_K.gguf new file mode 100644 index 0000000..d61813f --- /dev/null +++ b/Llama3.2-3B-Enigma.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd782424f3ea3d362e3b8e5a57026c927c8662ad2129a870fd96d14c182436be +size 1363936928 diff --git a/Llama3.2-3B-Enigma.Q3_K_L.gguf b/Llama3.2-3B-Enigma.Q3_K_L.gguf new file mode 100644 index 0000000..e30e128 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0009c37188cc5db64f15b82fcb13c691c236e30f4f517960a6c8dc88f79510b0 +size 1815348896 diff --git a/Llama3.2-3B-Enigma.Q3_K_M.gguf b/Llama3.2-3B-Enigma.Q3_K_M.gguf new file mode 100644 index 0000000..2fdf81e --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:686b255ceeeadf85da2121ab8266f1702c733b7763fc4ad4fd49769901ee0746 +size 1687160480 diff --git a/Llama3.2-3B-Enigma.Q3_K_S.gguf b/Llama3.2-3B-Enigma.Q3_K_S.gguf new file mode 100644 index 0000000..2d4ca48 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94778b87eed87910f636599d7974a8696d803e1cf4d09bd257350f4e74160ac7 +size 1542850208 diff --git a/Llama3.2-3B-Enigma.Q4_0_4_4.gguf b/Llama3.2-3B-Enigma.Q4_0_4_4.gguf new file mode 100644 index 0000000..a39e697 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bea2bf52c4b9141c6c1c487ae8d77c1f82a0779ddc179eda7c421aeb0bcebd9 +size 1917191840 diff --git a/Llama3.2-3B-Enigma.Q4_K_M.gguf b/Llama3.2-3B-Enigma.Q4_K_M.gguf new file mode 100644 index 0000000..2f659a0 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1f0b82603f299afc9e2938c49891a3de5c5d0009c7dbcad5327413cf6d0190 +size 2019378848 diff --git a/Llama3.2-3B-Enigma.Q4_K_S.gguf b/Llama3.2-3B-Enigma.Q4_K_S.gguf new file mode 100644 index 0000000..2fd0e43 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c624e22e8c2af0200629d19f512ee71b964a44a3fea1136dfc8364565a4e97ed +size 1928201888 diff --git a/Llama3.2-3B-Enigma.Q5_K_M.gguf b/Llama3.2-3B-Enigma.Q5_K_M.gguf new file mode 100644 index 0000000..79b9087 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286d57b370e5950f09cb3263bb96a34f8d1d6f9824903ba6b10fac3645f2dec2 +size 2322155168 diff --git a/Llama3.2-3B-Enigma.Q5_K_S.gguf b/Llama3.2-3B-Enigma.Q5_K_S.gguf new file mode 100644 index 0000000..e08c7b6 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31925f16db34dd5ec5bd147d255c094712764d1d890100c04ecfeb923539fe59 +size 2269513376 diff --git a/Llama3.2-3B-Enigma.Q6_K.gguf b/Llama3.2-3B-Enigma.Q6_K.gguf new file mode 100644 index 0000000..799619b --- /dev/null +++ b/Llama3.2-3B-Enigma.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28381e28c397980a0ea4352a2f39df005a00f83682d139524ed270f59beece5d +size 2643855008 diff --git a/Llama3.2-3B-Enigma.Q8_0.gguf b/Llama3.2-3B-Enigma.Q8_0.gguf new file mode 100644 index 0000000..b69d50c --- /dev/null +++ b/Llama3.2-3B-Enigma.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1297f5fa0a9a465ab2fd87a19e1b3f166162f09390120d8725f90e572a690133 +size 3421900448 diff --git a/Llama3.2-3B-Enigma.f16.gguf b/Llama3.2-3B-Enigma.f16.gguf new file mode 100644 index 0000000..54cca72 --- /dev/null +++ b/Llama3.2-3B-Enigma.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19e9e3666e9d124a9bebc89a5854c7e69b0b52df92e408881e82469e8b884b2a +size 6433689248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..48c1ad9 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: ValiantLabs/Llama3.2-3B-Enigma +datasets: +- sequelbox/Tachibana +- sequelbox/Supernova +language: +- en +library_name: transformers +license: llama3.2 +model_type: llama +quantized_by: mradermacher +tags: +- enigma +- valiant +- valiant-labs +- llama +- llama-3.2 +- llama-3.2-instruct +- llama-3.2-instruct-3b +- llama-3 +- llama-3-instruct +- llama-3-instruct-3b +- 3b +- code +- code-instruct +- python +- conversational +- chat +- instruct +--- +## About + + + + + + +static quants of https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-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/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Enigma-GGUF/resolve/main/Llama3.2-3B-Enigma.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. + +