commit 729bf3993e8264cdd9a8f715bc3f7b7c3aa849c1 Author: ModelHub XC Date: Wed Sep 30 13:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..72c37cb --- /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 +colombian-conflict-chat-Llama3.1-f16.f16.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +colombian-conflict-chat-Llama3.1-f16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..586e400 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: jdavit/colombian-conflict-chat-Llama3.1-f16 +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/jdavit/colombian-conflict-chat-Llama3.1-f16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#colombian-conflict-chat-Llama3.1-f16-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/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/colombian-conflict-chat-Llama3.1-f16-GGUF/resolve/main/colombian-conflict-chat-Llama3.1-f16.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. + + diff --git a/colombian-conflict-chat-Llama3.1-f16.IQ4_XS.gguf b/colombian-conflict-chat-Llama3.1-f16.IQ4_XS.gguf new file mode 100644 index 0000000..2751be1 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:441d9a103cf2b4aa577cecbeea711c064aa08f39f681d9fe3a59412da43fb3ff +size 4484363776 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q2_K.gguf b/colombian-conflict-chat-Llama3.1-f16.Q2_K.gguf new file mode 100644 index 0000000..346fe10 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc9df584049a0a8de4e2e7be6f47e88ca6506b49d8a6d2c8afd0d2012127015 +size 3179132416 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q3_K_L.gguf b/colombian-conflict-chat-Llama3.1-f16.Q3_K_L.gguf new file mode 100644 index 0000000..78b16e9 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad6d1f591f29db0502f9fdb5d1949c0e419c29040b3934ad46ce639f90c3629 +size 4321957376 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q3_K_M.gguf b/colombian-conflict-chat-Llama3.1-f16.Q3_K_M.gguf new file mode 100644 index 0000000..071f1a9 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d234510376ac16378baabf34a50d1514c87fe764c9b0b7414a272ae6450d19b4 +size 4018918912 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q3_K_S.gguf b/colombian-conflict-chat-Llama3.1-f16.Q3_K_S.gguf new file mode 100644 index 0000000..ba00b91 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c2666717102c491a9bbc339ad2755d61b42b9cc06dfc4159e259ae96aa40c6 +size 3664500224 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q4_K_M.gguf b/colombian-conflict-chat-Llama3.1-f16.Q4_K_M.gguf new file mode 100644 index 0000000..067b08e --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e0276f5cf5a9b8877b9d231f049ce34b02f86a74b7b20b9d14592ff2f2ddb6 +size 4920735232 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q4_K_S.gguf b/colombian-conflict-chat-Llama3.1-f16.Q4_K_S.gguf new file mode 100644 index 0000000..37d98e9 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e25d036c993fd7004899fb49df3770e820d100947f9e07021273212c66823631 +size 4692669952 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q5_K_M.gguf b/colombian-conflict-chat-Llama3.1-f16.Q5_K_M.gguf new file mode 100644 index 0000000..f7a70b1 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c8be64259a53af06c6bac8a86547e2846a43fd726ddf2f1dbf36db5b794be9 +size 5732988416 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q5_K_S.gguf b/colombian-conflict-chat-Llama3.1-f16.Q5_K_S.gguf new file mode 100644 index 0000000..2ca2674 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf6ce907051cf136d2b9f2bbeb0e09ddf2f68b84365088d28875cf93b28866c +size 5599294976 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q6_K.gguf b/colombian-conflict-chat-Llama3.1-f16.Q6_K.gguf new file mode 100644 index 0000000..adabe63 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509d2b67290d9d41693d0b6e042353b9d577cebc0c94dd6be8d162eaa2172ac4 +size 6596007424 diff --git a/colombian-conflict-chat-Llama3.1-f16.Q8_0.gguf b/colombian-conflict-chat-Llama3.1-f16.Q8_0.gguf new file mode 100644 index 0000000..307110d --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292f5a6f3d3b93465d806c070f4021e5b3c3c7428f6e7b03e234ee66965b1031 +size 8540771840 diff --git a/colombian-conflict-chat-Llama3.1-f16.f16.gguf b/colombian-conflict-chat-Llama3.1-f16.f16.gguf new file mode 100644 index 0000000..4f1ff67 --- /dev/null +++ b/colombian-conflict-chat-Llama3.1-f16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7070fd10dfd4c1239ed7fd98be4e4a0b7b76094e4d12fbf217e71ae7ecb2d5f +size 16068892160