commit fb4f10aec0eef34dd6c8646431429b2975333f1b Author: ModelHub XC Date: Tue Apr 28 23:32:36 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8572b6e --- /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 +Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Infinity-Instruct-3M-0625-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.IQ4_XS.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..40da520 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365d61d48b73c31f51c057d6b28ff99d1ee012d326c81954e2c6cca12302e345 +size 4484363584 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q2_K.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..b37158a --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b085a90cdaf4002d94e2974581b16d1bb245f61a967d0f2cb8e49ada3b569f46 +size 3179132224 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_L.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..6d6f3bd --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c86948942d0be41fe1efe3ad87ae3ce040f411535e7439037e22699b7f66c60 +size 4321957184 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_M.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..54d5ee3 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5148a60f1602638bd6a4c9bf9c5979ea927b96c9b04c3d50a3b184f8cf4098 +size 4018918720 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_S.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9075f3d --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c2d5f40a03666cf6e419af26369d9b878232b0d3befbc8d0e5341692d343b2 +size 3664500032 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_M.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bdc8e31 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab58b8cf757fb9ca591221d5e1b55943bdf640633365e6fcedfc7647cd9d0f7 +size 4920735040 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_S.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..20c4df7 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d7404a208d1251458184b2e98cca3486e13451e2628d74abb3e5973df3d333 +size 4692669760 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_M.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..791dff8 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2207b59a1e67177f85042e08d0a651f63a464ba94a1c8204a4264c3198fb606 +size 5732988224 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_S.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1bb72ae --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a72c117361c40f53972e883147110703feaa1c00e0655e3ac6d4336c238d14 +size 5599294784 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q6_K.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..ce6cabc --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cac578e0be67587283f4eb0318389a4349f35133a36e1d1a2c78a750e937a9b +size 6596007232 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.Q8_0.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..ae8b757 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f35e2ce1fb9045db56df5012280790823b104cc52f2c76987d72b4563dd5b4d +size 8540771648 diff --git a/Infinity-Instruct-3M-0625-Llama3-8B.f16.gguf b/Infinity-Instruct-3M-0625-Llama3-8B.f16.gguf new file mode 100644 index 0000000..b8e4940 --- /dev/null +++ b/Infinity-Instruct-3M-0625-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6df26f91d01516851d9faf536e8de03cfa51208a264fee59e84d25113f35b3 +size 16068891968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1f225c8 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: BAAI/Infinity-Instruct-3M-0625-Llama3-8B +datasets: +- BAAI/Infinity-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BAAI/Infinity-Instruct-3M-0625-Llama3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-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/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Infinity-Instruct-3M-0625-Llama3-8B-GGUF/resolve/main/Infinity-Instruct-3M-0625-Llama3-8B.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. + +