commit 0007c84982f64632aa314bf7d77435a73d50c472 Author: ModelHub XC Date: Mon Apr 27 07:28:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2dfc7cf --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama-DNA-1.0-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-DNA-1.0-8B-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-DNA-1.0-8B-Instruct.IQ4_XS.gguf b/Llama-DNA-1.0-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..3b53c3b --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd58f63d9788acf4060f32561a51ac72da351ca92296f3bee6dc3a34694de09 +size 4484364064 diff --git a/Llama-DNA-1.0-8B-Instruct.Q2_K.gguf b/Llama-DNA-1.0-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..3711288 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106b71843a1d69684609fcea289a3e37b361777db9e35890eeb57df51d13a56d +size 3179132704 diff --git a/Llama-DNA-1.0-8B-Instruct.Q3_K_L.gguf b/Llama-DNA-1.0-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..d6aba7b --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399716dae14858d7a354bcaa1d0956afb66b00d8cc570fe68a8af7fa60a05ef7 +size 4321957664 diff --git a/Llama-DNA-1.0-8B-Instruct.Q3_K_M.gguf b/Llama-DNA-1.0-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e5bc922 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14aa369e60cc0df7e7783b7beee1e58f9129344bf858ea0124a8c8306b56d652 +size 4018919200 diff --git a/Llama-DNA-1.0-8B-Instruct.Q3_K_S.gguf b/Llama-DNA-1.0-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..5a349af --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00e173a4ca5b19fd8bfebe04689c41468ed27e89a26ef96181cdf3ccb63ce91 +size 3664500512 diff --git a/Llama-DNA-1.0-8B-Instruct.Q4_0_4_4.gguf b/Llama-DNA-1.0-8B-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..7cdb357 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d15f5a66fbb4693243e063f4ade26e8d8a7abcc836bbf1dc618ea05b65ac15 +size 4661212960 diff --git a/Llama-DNA-1.0-8B-Instruct.Q4_K_M.gguf b/Llama-DNA-1.0-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..efe0066 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3a15773027a8cc2763b7d7b78e6205f62916cdf23c82169ed7e71d314cef92 +size 4920735520 diff --git a/Llama-DNA-1.0-8B-Instruct.Q4_K_S.gguf b/Llama-DNA-1.0-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..71de905 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ee36a7ec59ae67f6317091fdc38285ec0bdfab1be591537f061d12a9a5cacf2 +size 4692670240 diff --git a/Llama-DNA-1.0-8B-Instruct.Q5_K_M.gguf b/Llama-DNA-1.0-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8702436 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36c32ecb19506e0f376f46d5d9320974f77ce6e2216348b977d37430862cb45a +size 5732988704 diff --git a/Llama-DNA-1.0-8B-Instruct.Q5_K_S.gguf b/Llama-DNA-1.0-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..0f6557a --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93e04e2b1921f77e7521860deca27cf116bc83f0719444104ec2e6f87028754 +size 5599295264 diff --git a/Llama-DNA-1.0-8B-Instruct.Q6_K.gguf b/Llama-DNA-1.0-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..061f93f --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56010198e89ae4cb83a7645d441435cac87fa860ee8e87a01d69752242eaf805 +size 6596007712 diff --git a/Llama-DNA-1.0-8B-Instruct.Q8_0.gguf b/Llama-DNA-1.0-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..f4e44a2 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4d587bd91baeba5f1972c11e99ff61b426072dfd65255bedf68eb8a2eeed38 +size 8540772128 diff --git a/Llama-DNA-1.0-8B-Instruct.f16.gguf b/Llama-DNA-1.0-8B-Instruct.f16.gguf new file mode 100644 index 0000000..9805025 --- /dev/null +++ b/Llama-DNA-1.0-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61638dba195e3a5447776b5f95da3c61d529d8fed5ae8874af48b10d3afcd241 +size 16068892448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..91d2f5a --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: dnotitia/Llama-DNA-1.0-8B-Instruct +language: +- en +- ko +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- dnotitia +- nlp +- llm +- slm +- conversation +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/dnotitia/Llama-DNA-1.0-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-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/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-DNA-1.0-8B-Instruct-GGUF/resolve/main/Llama-DNA-1.0-8B-Instruct.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +