commit b9a495f3f64ca56921b06e738f686081cc7a03c1 Author: ModelHub XC Date: Sat May 9 09:54:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e034df --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Meta-Llama-3-8B-Instruct-function-calling.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-Instruct-function-calling.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-Instruct-function-calling.IQ3_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_M.gguf new file mode 100644 index 0000000..91273d5 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7370d95147e9bf5131056203beb7432e484b4b92ac3cd1c0e8ef8282dfa0b622 +size 3784824448 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.IQ3_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_S.gguf new file mode 100644 index 0000000..d8d94ce --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea1b53b06f17bfca66f4ee52a40b9f87844e8af72d5cd7803e55147d484341f +size 3682326144 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.IQ3_XS.gguf b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_XS.gguf new file mode 100644 index 0000000..0a662d6 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c01a04ade5f1ec5018d2d8bfca98863f377a720525bedf51e640bf1a3143db +size 3518748288 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.IQ4_XS.gguf b/Meta-Llama-3-8B-Instruct-function-calling.IQ4_XS.gguf new file mode 100644 index 0000000..4025f93 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1514e41a6795bb2324818317d1b4fdcc6557cd35bc34cc0b1331c9b22ec73173 +size 4484363904 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q2_K.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q2_K.gguf new file mode 100644 index 0000000..a2c5c46 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69d51128c4ac16ac5f659b4ecd052ba532025ab15ea4986a4b80163fbac1175 +size 3179132544 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_L.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_L.gguf new file mode 100644 index 0000000..af1a019 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d7889d6a3d35d3b4604b477d0a8b424b47b9dd3bb50e874f4534ad9e113038 +size 4321957504 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_M.gguf new file mode 100644 index 0000000..f96c81c --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5079f32991aa731ae216fb5b52619cef7ec3c0ab5d08917ca6b946eeb9092197 +size 4018919040 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_S.gguf new file mode 100644 index 0000000..dfc57ba --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c69625f086f4a1c95c52595931d6c3624e80bc9a39cd4df727e38bff4cdaa33 +size 3664500352 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_M.gguf new file mode 100644 index 0000000..705fb08 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0def47955740d350ac07008aea78151eb1e4243303d59969570fa402faffa3de +size 4920735360 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_S.gguf new file mode 100644 index 0000000..aeacd0e --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5d15ee4484a000453937fbcd0b905d772ef41879d9cdfebafaebb8027f0dd4 +size 4692670080 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_M.gguf new file mode 100644 index 0000000..60ff1c5 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d988d3d14e0f4d8ea7a0197cdc46942ed72eebde32edb0b9dae5fe5a2e14c0 +size 5732988544 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_S.gguf new file mode 100644 index 0000000..dd62150 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abea9c1c80c2083de65fdc0efa251e1833854c96980235c3d59241227f807cb +size 5599295104 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q6_K.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q6_K.gguf new file mode 100644 index 0000000..e9be254 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e203ede6c9f2d36bfae067b0e46fd5dfb2c9788d82d120876cea8c4f612d13 +size 6596007552 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.Q8_0.gguf b/Meta-Llama-3-8B-Instruct-function-calling.Q8_0.gguf new file mode 100644 index 0000000..4e54afb --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e6ffa1c3a7006f5faf78752991f0f8c6bbab2ae2f4fbe882c41978d704a662 +size 8540771968 diff --git a/Meta-Llama-3-8B-Instruct-function-calling.f16.gguf b/Meta-Llama-3-8B-Instruct-function-calling.f16.gguf new file mode 100644 index 0000000..ced4d18 --- /dev/null +++ b/Meta-Llama-3-8B-Instruct-function-calling.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb40eaef86a9d08c12236eb231c12043a73cb624233fb376ed6329dfcc4b096 +size 16068892288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..71e7be6 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Trelis/Meta-Llama-3-8B-Instruct-function-calling +datasets: +- Trelis/function_calling_v3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- llama 3 +--- +## About + + + + + + +static quants of https://huggingface.co/Trelis/Meta-Llama-3-8B-Instruct-function-calling + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-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/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-function-calling-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-function-calling.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. + +