commit a870adfcf8a293fb044c9f48e36b5399227555f3 Author: ModelHub XC Date: Wed Jun 3 13:42:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5c8da51 --- /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 +Esmeralda-Llama-3.1-8B-control.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.f16.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Esmeralda-Llama-3.1-8B-control.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Esmeralda-Llama-3.1-8B-control.IQ4_XS.gguf b/Esmeralda-Llama-3.1-8B-control.IQ4_XS.gguf new file mode 100644 index 0000000..e4f2889 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26493edc5481cb6269935caf4eae6d64799c123186930e4b4a9d804b74f5b21 +size 4484363936 diff --git a/Esmeralda-Llama-3.1-8B-control.Q2_K.gguf b/Esmeralda-Llama-3.1-8B-control.Q2_K.gguf new file mode 100644 index 0000000..0185e92 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0484a01884bff4564f2d9f7e274e4788e14dec60cbb53194b8ab6ad0f016a013 +size 3179132576 diff --git a/Esmeralda-Llama-3.1-8B-control.Q3_K_L.gguf b/Esmeralda-Llama-3.1-8B-control.Q3_K_L.gguf new file mode 100644 index 0000000..661bba8 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078e58b350295f2f9b1758c7051fb5414aa8a0f81df657bda5635c997a8f10c7 +size 4321957536 diff --git a/Esmeralda-Llama-3.1-8B-control.Q3_K_M.gguf b/Esmeralda-Llama-3.1-8B-control.Q3_K_M.gguf new file mode 100644 index 0000000..b949b54 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38fdf495ac14baa75005d5a5c27155577017b80e1ee1a3e0edf90ba05c7cc22 +size 4018919072 diff --git a/Esmeralda-Llama-3.1-8B-control.Q3_K_S.gguf b/Esmeralda-Llama-3.1-8B-control.Q3_K_S.gguf new file mode 100644 index 0000000..819b61b --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b3583c0c85d37fcb5e1009f2da1b6c67ef36a003461ff86128d5e87aee05523 +size 3664500384 diff --git a/Esmeralda-Llama-3.1-8B-control.Q4_K_M.gguf b/Esmeralda-Llama-3.1-8B-control.Q4_K_M.gguf new file mode 100644 index 0000000..7924061 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bdf43507b95ca1f44356be177129a4613e13ff28c73e7cd0ee1c1122ed03fb7 +size 4920735392 diff --git a/Esmeralda-Llama-3.1-8B-control.Q4_K_S.gguf b/Esmeralda-Llama-3.1-8B-control.Q4_K_S.gguf new file mode 100644 index 0000000..3c0c0ee --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578f396e151d0aff08e2d6a71b8b17c3a4133ff32b445e4d0660c3a1eb902274 +size 4692670112 diff --git a/Esmeralda-Llama-3.1-8B-control.Q5_K_M.gguf b/Esmeralda-Llama-3.1-8B-control.Q5_K_M.gguf new file mode 100644 index 0000000..7d10c94 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4716e0af7a4a09de62d66620851bddee7e244695a9350a8847e21730ecc285b9 +size 5732988576 diff --git a/Esmeralda-Llama-3.1-8B-control.Q5_K_S.gguf b/Esmeralda-Llama-3.1-8B-control.Q5_K_S.gguf new file mode 100644 index 0000000..f7f010e --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a64e61c37974a807c8cf58e1c04dce310638afc2d1090a1fa0d14568c9bf6a +size 5599295136 diff --git a/Esmeralda-Llama-3.1-8B-control.Q6_K.gguf b/Esmeralda-Llama-3.1-8B-control.Q6_K.gguf new file mode 100644 index 0000000..1df75d7 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b5293610f017d9d0b7553f8203a369af74eb906b25cd648b98cb71b1f836ae5 +size 6596007584 diff --git a/Esmeralda-Llama-3.1-8B-control.Q8_0.gguf b/Esmeralda-Llama-3.1-8B-control.Q8_0.gguf new file mode 100644 index 0000000..ec15daa --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358b14f747386601fd171ece162acef89a5cd3724d6dd730b08fb9834fc63323 +size 8540772000 diff --git a/Esmeralda-Llama-3.1-8B-control.f16.gguf b/Esmeralda-Llama-3.1-8B-control.f16.gguf new file mode 100644 index 0000000..f254d15 --- /dev/null +++ b/Esmeralda-Llama-3.1-8B-control.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5de39477c0be122b3cc41abf9a1766bda53866c77021d6584bbe4908c39ed7 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eaea40d --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: Locutusque/Esmeralda-Llama-3.1-8B-control +datasets: +- Locutusque/esmeralda-agentic +language: +- en +library_name: transformers +license: llama3.1 +model_creator: Locutusque +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- agent +- tool-use +- function-calling +- llama-3.1 +- text-generation-inference +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Locutusque/Esmeralda-Llama-3.1-8B-control + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Esmeralda-Llama-3.1-8B-control-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-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/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Esmeralda-Llama-3.1-8B-control-GGUF/resolve/main/Esmeralda-Llama-3.1-8B-control.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. + +