commit 8050102e824893bace91cce74b00cdd2de7b31ce Author: ModelHub XC Date: Sun May 31 01:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..13d0051 --- /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 +Llama-3.1-Lafeak-8B-Primer-Non-Q.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafeak-8B-Primer-Non-Q.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.IQ4_XS.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.IQ4_XS.gguf new file mode 100644 index 0000000..704b02b --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ccb307122b9cc453717efd886569d7effc9a97a7dd0344074dfd03533d990b +size 4484363744 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q2_K.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q2_K.gguf new file mode 100644 index 0000000..63cccc1 --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ff6663751fa9e8d018a3fc5d3e0a936867bf2d6f8609472b392e173fc086f1 +size 3179132384 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_L.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_L.gguf new file mode 100644 index 0000000..c95d39b --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:424c443860afe0102429f2032fd860a04253f3b029d339620e88cae9c058d9c0 +size 4321957344 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_M.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_M.gguf new file mode 100644 index 0000000..97c8bb1 --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bdde6198787d76ff6b7f220dd963db42ecf05f2a419868b6c66576ac162aef7 +size 4018918880 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_S.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_S.gguf new file mode 100644 index 0000000..4f7cdef --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30ac6aa6fee2659f035bcc6a7d485ae4fbe4334a4adfb0c0b158882c65fef6b +size 3664500192 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_M.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_M.gguf new file mode 100644 index 0000000..47399ee --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4a12821caf18644dbc95e220b0f7b638053c2fadda212441ca63ff4a221561 +size 4920735200 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_S.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_S.gguf new file mode 100644 index 0000000..6e97a54 --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9130846c1a5c21523cc75ece4323315b7fbe5efa09cbff5039998207ef7dade9 +size 4692669920 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_M.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_M.gguf new file mode 100644 index 0000000..4f9f1b8 --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db2908417a82ee0210ffbf7300a284c96c330435b0ec565c59d2f70ba505ad2 +size 5732988384 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_S.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_S.gguf new file mode 100644 index 0000000..ef6ff3a --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad3e4266eb6d31a23410b8f474a9ee5e187cc390d2c833454c6772e9b9857b5a +size 5599294944 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q6_K.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q6_K.gguf new file mode 100644 index 0000000..36e61bf --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848e1f8423612caa6484c7d71e37de7c62bab9483ec75aa19b92caba8e5b7f4f +size 6596007392 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q8_0.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q8_0.gguf new file mode 100644 index 0000000..39a5426 --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5e0733a6624794a7dc1865ea11d0bc6ea6dd6fe1cc09a6ebcc62e409786282 +size 8540771808 diff --git a/Llama-3.1-Lafeak-8B-Primer-Non-Q.f16.gguf b/Llama-3.1-Lafeak-8B-Primer-Non-Q.f16.gguf new file mode 100644 index 0000000..7bd829b --- /dev/null +++ b/Llama-3.1-Lafeak-8B-Primer-Non-Q.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f5b49b8adfa040d03a9bf00d9e4c511807b788747fd765b2acdc299a5c98b9 +size 16068892128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..669c834 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Yuichi1218/Llama-3.1-Lafeak-8B-Primer-Non-Q +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuichi1218/Llama-3.1-Lafeak-8B-Primer-Non-Q + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Lafeak-8B-Primer-Non-Q-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/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafeak-8B-Primer-Non-Q-GGUF/resolve/main/Llama-3.1-Lafeak-8B-Primer-Non-Q.f16.gguf) | f16 | 16.2 | 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. + +