commit f04fe7f2bb08327f216beb47791a67767cf519cc Author: ModelHub XC Date: Fri Jun 26 06:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lancer-1-1b-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dfdd6f2 --- /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 +Lancer-1-1b-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lancer-1-1b-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lancer-1-1b-Instruct.IQ4_XS.gguf b/Lancer-1-1b-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..32819fe --- /dev/null +++ b/Lancer-1-1b-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b5fbbe671adf52ec540554814b9c39c205aaad8c781442fa5a77c68bd6a2563 +size 748385696 diff --git a/Lancer-1-1b-Instruct.Q2_K.gguf b/Lancer-1-1b-Instruct.Q2_K.gguf new file mode 100644 index 0000000..522a118 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c492fd3bb8c8b9d898e7655f383f88b7b8025ec0e91ec72f6811cfd308bc5ddc +size 580875680 diff --git a/Lancer-1-1b-Instruct.Q3_K_L.gguf b/Lancer-1-1b-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e4af5c8 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b6f50ae9131e57debfd97a597380b708e63d478901c878e616145fc43ee7a01 +size 732525984 diff --git a/Lancer-1-1b-Instruct.Q3_K_M.gguf b/Lancer-1-1b-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..81cb000 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408eade2374d4fd9cc744b10ca9b6c545e3765b04c8e502c0970dc775f8dd818 +size 690845088 diff --git a/Lancer-1-1b-Instruct.Q3_K_S.gguf b/Lancer-1-1b-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a11353f --- /dev/null +++ b/Lancer-1-1b-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13dd9cbd0dea243ec60907ef4c524af1bbf797cf6741414063edc4d5b9be4de8 +size 641693088 diff --git a/Lancer-1-1b-Instruct.Q4_K_M.gguf b/Lancer-1-1b-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..eefeebd --- /dev/null +++ b/Lancer-1-1b-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f49d0c58ad351f086f314404748388c0712fb5d8638dd0af7242f48daa1583 +size 807695776 diff --git a/Lancer-1-1b-Instruct.Q4_K_S.gguf b/Lancer-1-1b-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..cb77bc0 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4891abd5f87a9f7278cc25503854f6813da717e7232a90d3eecdaad4ebc9db72 +size 775648672 diff --git a/Lancer-1-1b-Instruct.Q5_K_M.gguf b/Lancer-1-1b-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..cf185f0 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:964d1384b37f7197e85b2a0edabf2de0330a026724e4cf5b8b24213cb74ff90f +size 911504800 diff --git a/Lancer-1-1b-Instruct.Q5_K_S.gguf b/Lancer-1-1b-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..53a47de --- /dev/null +++ b/Lancer-1-1b-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3e6d28ce1c6cf75b51a5e87949ee6e398e79b2cab6dd3260019ceebe7e658d +size 892564896 diff --git a/Lancer-1-1b-Instruct.Q6_K.gguf b/Lancer-1-1b-Instruct.Q6_K.gguf new file mode 100644 index 0000000..45daac6 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa79099ae96963743f81dc1b8cb032e9421e6d014fbd26a1e332395040c0fb0d +size 1021801888 diff --git a/Lancer-1-1b-Instruct.Q8_0.gguf b/Lancer-1-1b-Instruct.Q8_0.gguf new file mode 100644 index 0000000..3035e60 --- /dev/null +++ b/Lancer-1-1b-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c220b2ec37b48d6a1ab633cd6d85ae24a5ffbd5c6ad0b49c6d143e712f35424e +size 1321084320 diff --git a/Lancer-1-1b-Instruct.f16.gguf b/Lancer-1-1b-Instruct.f16.gguf new file mode 100644 index 0000000..ed11111 --- /dev/null +++ b/Lancer-1-1b-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:617b53c03bb0788f7b034ef5c132073e5a81f453b324a51f610698a9cbc77b2e +size 2479596960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a5a4a4f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: kavonalds/Lancer-1-1b-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/kavonalds/Lancer-1-1b-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Lancer-1-1b-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/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lancer-1-1b-Instruct-GGUF/resolve/main/Lancer-1-1b-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. + +