From 318213c820fa09ebc0e80ae2678f4001c6f4ecc4 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 2 Aug 2026 07:45:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: second-state/Llama-2-13B-Chat-GGUF Source: Original Platform --- .gitattributes | 36 +++++++++++++ Llama-2-13b-chat-hf-Q2_K.gguf | 3 ++ Llama-2-13b-chat-hf-Q3_K_L.gguf | 3 ++ Llama-2-13b-chat-hf-Q3_K_M.gguf | 3 ++ Llama-2-13b-chat-hf-Q3_K_S.gguf | 3 ++ Llama-2-13b-chat-hf-Q4_0.gguf | 3 ++ Llama-2-13b-chat-hf-Q4_K_M.gguf | 3 ++ Llama-2-13b-chat-hf-Q4_K_S.gguf | 3 ++ Llama-2-13b-chat-hf-Q5_0.gguf | 3 ++ Llama-2-13b-chat-hf-Q5_K_M.gguf | 3 ++ Llama-2-13b-chat-hf-Q5_K_S.gguf | 3 ++ Llama-2-13b-chat-hf-Q6_K.gguf | 3 ++ Llama-2-13b-chat-hf-Q8_0.gguf | 3 ++ Llama-2-13b-chat-hf-f16.gguf | 3 ++ README.md | 89 +++++++++++++++++++++++++++++++++ config.json | 1 + configuration.json | 1 + llama-2-13b-chat.Q5_K_M.gguf | 3 ++ 18 files changed, 169 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-2-13b-chat-hf-Q2_K.gguf create mode 100644 Llama-2-13b-chat-hf-Q3_K_L.gguf create mode 100644 Llama-2-13b-chat-hf-Q3_K_M.gguf create mode 100644 Llama-2-13b-chat-hf-Q3_K_S.gguf create mode 100644 Llama-2-13b-chat-hf-Q4_0.gguf create mode 100644 Llama-2-13b-chat-hf-Q4_K_M.gguf create mode 100644 Llama-2-13b-chat-hf-Q4_K_S.gguf create mode 100644 Llama-2-13b-chat-hf-Q5_0.gguf create mode 100644 Llama-2-13b-chat-hf-Q5_K_M.gguf create mode 100644 Llama-2-13b-chat-hf-Q5_K_S.gguf create mode 100644 Llama-2-13b-chat-hf-Q6_K.gguf create mode 100644 Llama-2-13b-chat-hf-Q8_0.gguf create mode 100644 Llama-2-13b-chat-hf-f16.gguf create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 llama-2-13b-chat.Q5_K_M.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-13b-chat-hf-Q2_K.gguf b/Llama-2-13b-chat-hf-Q2_K.gguf new file mode 100644 index 0000000..bae8dac --- /dev/null +++ b/Llama-2-13b-chat-hf-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0816715dba97ecd645265f3fbdb86e4e07f50c5546a28b1e1fbf9da80ae12e6d +size 5429349184 diff --git a/Llama-2-13b-chat-hf-Q3_K_L.gguf b/Llama-2-13b-chat-hf-Q3_K_L.gguf new file mode 100644 index 0000000..d0e3688 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a875c6622c43b1bda40928efbd9052e90f5e1ebec5759f445b4eada8ced1ee +size 6929560384 diff --git a/Llama-2-13b-chat-hf-Q3_K_M.gguf b/Llama-2-13b-chat-hf-Q3_K_M.gguf new file mode 100644 index 0000000..6015daa --- /dev/null +++ b/Llama-2-13b-chat-hf-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c027d6379debd8431d64fbf94b2756b7034e59b98cd21b9659b1cbbdcdbeb3 +size 6337770304 diff --git a/Llama-2-13b-chat-hf-Q3_K_S.gguf b/Llama-2-13b-chat-hf-Q3_K_S.gguf new file mode 100644 index 0000000..14fd152 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680d1688a2ec54aeaf83c66ac9e892890ba339be695e7407ac2491435704953d +size 5658981184 diff --git a/Llama-2-13b-chat-hf-Q4_0.gguf b/Llama-2-13b-chat-hf-Q4_0.gguf new file mode 100644 index 0000000..def1159 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1405908d71ad9167436b6d5d41bf239957201e621ef528851882a3a72472fa +size 7365835584 diff --git a/Llama-2-13b-chat-hf-Q4_K_M.gguf b/Llama-2-13b-chat-hf-Q4_K_M.gguf new file mode 100644 index 0000000..f864047 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3831fb445fc73ac258b7ceae3c8ef56ba7e2c555dc1bb778f6db683136a09e +size 7865957184 diff --git a/Llama-2-13b-chat-hf-Q4_K_S.gguf b/Llama-2-13b-chat-hf-Q4_K_S.gguf new file mode 100644 index 0000000..40655ba --- /dev/null +++ b/Llama-2-13b-chat-hf-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39337b505435ab694020399911e0d88260c499e6cf86385b028c34c6f6f1a6a7 +size 7414332224 diff --git a/Llama-2-13b-chat-hf-Q5_0.gguf b/Llama-2-13b-chat-hf-Q5_0.gguf new file mode 100644 index 0000000..3903711 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4774182ce45e02c924ed6a63c5c54bed7688965e23e69f2e4b3a00951f04c3 +size 8972286784 diff --git a/Llama-2-13b-chat-hf-Q5_K_M.gguf b/Llama-2-13b-chat-hf-Q5_K_M.gguf new file mode 100644 index 0000000..5a28fe1 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c08278e8ed7ae96e25e8968e77ba8fc4ae8b974a8b47a105880756f8f82f3e +size 9229925184 diff --git a/Llama-2-13b-chat-hf-Q5_K_S.gguf b/Llama-2-13b-chat-hf-Q5_K_S.gguf new file mode 100644 index 0000000..e8b93a6 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d796e7f61ac5be78d48e32a78cb9e027f9a4951ff5294780c0a84091eac6e9 +size 8972286784 diff --git a/Llama-2-13b-chat-hf-Q6_K.gguf b/Llama-2-13b-chat-hf-Q6_K.gguf new file mode 100644 index 0000000..cf88a5a --- /dev/null +++ b/Llama-2-13b-chat-hf-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f699dc60156be802237b592762f371821cc39ba04c189b7a5b4e9fdaa70910 +size 10679141184 diff --git a/Llama-2-13b-chat-hf-Q8_0.gguf b/Llama-2-13b-chat-hf-Q8_0.gguf new file mode 100644 index 0000000..0a22c14 --- /dev/null +++ b/Llama-2-13b-chat-hf-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68adfad7667e333ef169e43f6be11197120a4e773dc456a6fca183defcf5c0b3 +size 13831320384 diff --git a/Llama-2-13b-chat-hf-f16.gguf b/Llama-2-13b-chat-hf-f16.gguf new file mode 100644 index 0000000..30c5365 --- /dev/null +++ b/Llama-2-13b-chat-hf-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9dff1fce83e43c46a9f80e20a0f6374a55cacdfea8a058c1bf16e9303e6920 +size 26033304352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..507a798 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +language: +- en +license: llama2 +tags: +- facebook +- meta +- pytorch +- llama +- llama-2 +model_name: Llama 2 13B Chat +base_model: meta-llama/Llama-2-13b-chat-hf +inference: false +model_creator: Meta Llama 2 +model_type: llama +pipeline_tag: text-generation +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Llama-2-13B-Chat-GGUF + +## Original Model + +[meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `llama-2-chat` + + - Prompt string + + ```text + [INST] <> + {{ system_prompt }} + <> + + {{ user_msg_1 }} [/INST] {{ model_answer_1 }} [INST] {{ user_msg_2 }} [/INST] + ``` + +- Context size: `5120` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-13b-chat-hf-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template llama-2-chat \ + --ctx-size 5120 \ + --model-name llama-2-13b-chat + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-13b-chat-hf-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template llama-2-chat \ + --ctx-size 5120 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Llama-2-13b-chat-hf-Q2_K.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q2_K.gguf) | Q2_K | 2 | 5.43 GB| smallest, significant quality loss - not recommended for most purposes | +| [Llama-2-13b-chat-hf-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| small, substantial quality loss | +| [Llama-2-13b-chat-hf-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| very small, high quality loss | +| [Llama-2-13b-chat-hf-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| very small, high quality loss | +| [Llama-2-13b-chat-hf-Q4_0.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Llama-2-13b-chat-hf-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| medium, balanced quality - recommended | +| [Llama-2-13b-chat-hf-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| small, greater quality loss | +| [Llama-2-13b-chat-hf-Q5_0.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Llama-2-13b-chat-hf-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| large, very low quality loss - recommended | +| [Llama-2-7b-chat-hf-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| large, low quality loss - recommended | +| [Llama-2-13b-chat-hf-Q6_K.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q6_K.gguf) | Q6_K | 6 | 10.7 GB| very large, extremely low quality loss | +| [Llama-2-13b-chat-hf-Q8_0.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-Q8_0.gguf) | Q8_0 | 8 | 13.8 GB| very large, extremely low quality loss - not recommended | +| [Llama-2-13b-chat-hf-f16.gguf](https://huggingface.co/second-state/Llama-2-13B-Chat-GGUF/blob/main/Llama-2-13b-chat-hf-f16.gguf) | f16 | 16 | 26 GB| | diff --git a/config.json b/config.json new file mode 100644 index 0000000..a6dccd7 --- /dev/null +++ b/config.json @@ -0,0 +1 @@ +Repo model meta-llama/Llama-2-13b-chat-hf is gated. You must be authenticated to access it. \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/llama-2-13b-chat.Q5_K_M.gguf b/llama-2-13b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..db220b5 --- /dev/null +++ b/llama-2-13b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef36e090240040f97325758c1ad8e23f3801466a8eece3a9eac2d22d942f548a +size 9229924224