commit a289e7d506190f85d45b8cfdd3ff211fcd0afa22 Author: ModelHub XC Date: Tue Apr 21 19:03:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aaebca7 --- /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 +FuseChat-Llama-3.2-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-Llama-3.2-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-Llama-3.2-1B-Instruct.IQ4_XS.gguf b/FuseChat-Llama-3.2-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..89c12a1 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79daaa003cbabd45f7c44a49802a73ec48e87664861d1ec6a6eb5296a099ac10 +size 748381152 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q2_K.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..1d9de76 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad1618a5e9d26cc321fc56635ec46b07c7bc9e21c91dfd4238fbdf5a50b0ee8 +size 580871136 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q3_K_L.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..13bad96 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2192b30166d05af76487de0400e6054841adbd7763021f078cae5765b79eb878 +size 732521440 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q3_K_M.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0ad5148 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f58379a12fd4c8465ffc604718b833c10a5af0a82dc25362aa7e9154b85d41 +size 690840544 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q3_K_S.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..9e98437 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfeec385988e1ffd90a96d92aeedbb3580fc5516bec6fe26a15b0f3c45424fdc +size 641688544 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q4_K_M.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..390dd02 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a418898f26e5f7477a49020b8f58fac6efe5e20cfec294e8bd24599ea38dec79 +size 807691232 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q4_K_S.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..bded5ab --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98777b90d544b7705ff6415f37a2360092f6a96b21fad5307be105c79094074b +size 775644128 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q5_K_M.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..e918190 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d29195fa1fcc91d922c8e46ef21b9200d1f102335aef978c2241696bab44006 +size 911500256 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q5_K_S.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..a5fb38f --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ebd86b85413a01d7ed704d202739adfe59e161ee2681a168df27d9352c5c72 +size 892560352 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q6_K.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..54ad381 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed77eff2bb29c84c68dfcd338f7610a52a420643f672fa92e3fdb6c1f9dd7404 +size 1021797344 diff --git a/FuseChat-Llama-3.2-1B-Instruct.Q8_0.gguf b/FuseChat-Llama-3.2-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..d86ec21 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28f22fd7d11a2b90ad30578d1c57dcdef2029f79782b1e9315485724de75505c +size 1321079776 diff --git a/FuseChat-Llama-3.2-1B-Instruct.f16.gguf b/FuseChat-Llama-3.2-1B-Instruct.f16.gguf new file mode 100644 index 0000000..f15e587 --- /dev/null +++ b/FuseChat-Llama-3.2-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b15ab3e904136f16ffc4714577f8483b08cb1543aa9a560bb012ad335ceb05 +size 2479592416 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a06114c --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: FuseAI/FuseChat-Llama-3.2-1B-Instruct +datasets: +- FuseAI/FuseChat-3.0-DPO-Data +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FuseAI/FuseChat-Llama-3.2-1B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-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/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-Llama-3.2-1B-Instruct-GGUF/resolve/main/FuseChat-Llama-3.2-1B-Instruct.f16.gguf) | f16 | 2.6 | 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. + +