commit 7a37d2e52319a0e458b180056c8a4d67eadb3a4b Author: ModelHub XC Date: Wed Jun 3 22:54:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea86ffd --- /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 +Llama3.1-elm-turbo-4B-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-elm-turbo-4B-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-elm-turbo-4B-instruct.IQ3_M.gguf b/Llama3.1-elm-turbo-4B-instruct.IQ3_M.gguf new file mode 100644 index 0000000..f1bcf7c --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3973a2bfd438c37217c75074058c8cf3d210df1fec2d57ec3c1127a28062ce86 +size 2084717632 diff --git a/Llama3.1-elm-turbo-4B-instruct.IQ3_S.gguf b/Llama3.1-elm-turbo-4B-instruct.IQ3_S.gguf new file mode 100644 index 0000000..872f796 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b171e990ab41993702c544c6132aa1b16792bd513a1dc44322332a0211a778d5 +size 2019542080 diff --git a/Llama3.1-elm-turbo-4B-instruct.IQ3_XS.gguf b/Llama3.1-elm-turbo-4B-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..90133e1 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b309db418ddc5a0e088eb5fe7f28cffff1fed01adb9e54628322f764739f97d2 +size 1946403904 diff --git a/Llama3.1-elm-turbo-4B-instruct.IQ4_XS.gguf b/Llama3.1-elm-turbo-4B-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..0ae227d --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87be588128f8d4d70bca6a2be27f8f5bfb9ffb64abec0d9311b3b21b8dc64a7d +size 2405950528 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q2_K.gguf b/Llama3.1-elm-turbo-4B-instruct.Q2_K.gguf new file mode 100644 index 0000000..5293b3a --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7609ab9a15f580bf5ef2bebf9ef0977a9c073c6b42492d1020b58743d345247f +size 1771938880 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q3_K_L.gguf b/Llama3.1-elm-turbo-4B-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e1dde5c --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0ac2546072036d3f52d8c56a3b21e69033dc5e304b448837fb84d566227b0f +size 2317599808 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q3_K_M.gguf b/Llama3.1-elm-turbo-4B-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..3fe5dfe --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de008fe2ffc8297e9bbd84731d43f9ea203adc8da5f5d69959de58a736d4019 +size 2171323456 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q3_K_S.gguf b/Llama3.1-elm-turbo-4B-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..6d52a66 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04f61df07a531d3a809d0242eae7686162a72f5ffb592c4073e09195b1e8e1de +size 2006172736 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q4_K_M.gguf b/Llama3.1-elm-turbo-4B-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..9d5918f --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6900ea4444c8f24b9802b11d02c8361c1fe6da98a317870d429813167de15d36 +size 2594202688 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q4_K_S.gguf b/Llama3.1-elm-turbo-4B-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b05c5f0 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3256379cbd5a2b6f1cf59b31d7439514c0eb2954a9f8749d15deacd161a4302 +size 2503500864 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q5_K_M.gguf b/Llama3.1-elm-turbo-4B-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..c81ec9f --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de85ebea92db21452dc63d2033f129ceb711aa3c19e5d561021c2118c10c4d1b +size 2999608384 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q5_K_S.gguf b/Llama3.1-elm-turbo-4B-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d411dfb --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f35dbbce4a3619819d6518f7b5960e147c3728e3965d145f28c4fb3fbe7b64 +size 2946131008 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q6_K.gguf b/Llama3.1-elm-turbo-4B-instruct.Q6_K.gguf new file mode 100644 index 0000000..41be627 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfe0f6de84553eb9db94fca44238be3ea43f9e8477d7cafa14c43621c1c64bc +size 3430351936 diff --git a/Llama3.1-elm-turbo-4B-instruct.Q8_0.gguf b/Llama3.1-elm-turbo-4B-instruct.Q8_0.gguf new file mode 100644 index 0000000..b613084 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619321b9b942b1a4fc16cb999a0a5495f9f5eb33b0e57674bf09b6a82ac3a790 +size 4440572992 diff --git a/Llama3.1-elm-turbo-4B-instruct.f16.gguf b/Llama3.1-elm-turbo-4B-instruct.f16.gguf new file mode 100644 index 0000000..8fffa34 --- /dev/null +++ b/Llama3.1-elm-turbo-4B-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9250cbbff7adffb45f1741bb593068d9275ec0f46a92fc628370b29262a8b24a +size 8351106112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca77968 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: slicexai/Llama3.1-elm-turbo-4B-instruct +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/slicexai/Llama3.1-elm-turbo-4B-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-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/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.IQ3_XS.gguf) | IQ3_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q3_K_S.gguf) | Q3_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.IQ3_S.gguf) | IQ3_S | 2.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.IQ3_M.gguf) | IQ3_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q3_K_L.gguf) | Q3_K_L | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.IQ4_XS.gguf) | IQ4_XS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q4_K_S.gguf) | Q4_K_S | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q4_K_M.gguf) | Q4_K_M | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q5_K_S.gguf) | Q5_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q5_K_M.gguf) | Q5_K_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q6_K.gguf) | Q6_K | 3.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.Q8_0.gguf) | Q8_0 | 4.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-elm-turbo-4B-instruct-GGUF/resolve/main/Llama3.1-elm-turbo-4B-instruct.f16.gguf) | f16 | 8.5 | 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. + +