commit e0c7f3c6082878f0eb3b7a39956d54a79b244bff Author: ModelHub XC Date: Fri May 29 10:23:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Orca-2-13B-GGUF Source: Original Platform 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/Orca-2-13b-Q2_K.gguf b/Orca-2-13b-Q2_K.gguf new file mode 100644 index 0000000..2860258 --- /dev/null +++ b/Orca-2-13b-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922268ac740c6d94691d9b036e7afbabbc724740b041f0bda07cb4163c84d02d +size 5429366080 diff --git a/Orca-2-13b-Q3_K_L.gguf b/Orca-2-13b-Q3_K_L.gguf new file mode 100644 index 0000000..88b9f16 --- /dev/null +++ b/Orca-2-13b-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79157d96c6dd640856888154baa7de1e82e863cd23a6d650221c603fcdb24eb +size 6929578848 diff --git a/Orca-2-13b-Q3_K_M.gguf b/Orca-2-13b-Q3_K_M.gguf new file mode 100644 index 0000000..6b1667f --- /dev/null +++ b/Orca-2-13b-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f45e2189079ab23a8701a664e4ae62652a2bf26c97475bbc0f9d1f291d69dd0d +size 6337788768 diff --git a/Orca-2-13b-Q3_K_S.gguf b/Orca-2-13b-Q3_K_S.gguf new file mode 100644 index 0000000..295946a --- /dev/null +++ b/Orca-2-13b-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65fad78fc448db57493cb00bca7e19b5ad4ce3ea1042cf6cfb08f14c728bb3b +size 5658999648 diff --git a/Orca-2-13b-Q4_0.gguf b/Orca-2-13b-Q4_0.gguf new file mode 100644 index 0000000..3364c58 --- /dev/null +++ b/Orca-2-13b-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee7e4835b4ea5b8d80ce3cea9b57437b29446f9f409490b16db0276310db07d +size 7365856064 diff --git a/Orca-2-13b-Q4_K_M.gguf b/Orca-2-13b-Q4_K_M.gguf new file mode 100644 index 0000000..05dd581 --- /dev/null +++ b/Orca-2-13b-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d025231c42802368366400bec805650d84cb2701e579fc4160f407f7cc35f6 +size 7865977664 diff --git a/Orca-2-13b-Q4_K_S.gguf b/Orca-2-13b-Q4_K_S.gguf new file mode 100644 index 0000000..22490d5 --- /dev/null +++ b/Orca-2-13b-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edfe9d86abc26ec9ad7e58257ee1ff527c038e7fed85e86dd23ab704f1f8ba1d +size 7414352704 diff --git a/Orca-2-13b-Q5_0.gguf b/Orca-2-13b-Q5_0.gguf new file mode 100644 index 0000000..0d78e17 --- /dev/null +++ b/Orca-2-13b-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e75a8c73fd0d20fde873087d867343e748d8b0396692f3cecac4125d01cc8644 +size 8972309184 diff --git a/Orca-2-13b-Q5_K_M.gguf b/Orca-2-13b-Q5_K_M.gguf new file mode 100644 index 0000000..4b03dae --- /dev/null +++ b/Orca-2-13b-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104d8239756f5bc861d0c5a407035e894f54218bc2e32b7b7ae437bc8dc6079d +size 9229947584 diff --git a/Orca-2-13b-Q5_K_S.gguf b/Orca-2-13b-Q5_K_S.gguf new file mode 100644 index 0000000..c820498 --- /dev/null +++ b/Orca-2-13b-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad63d1ec55ad13dd1ffc67befd4928fbd3d6888fc76d466150b43fc598f12c6b +size 8972309184 diff --git a/Orca-2-13b-Q6_K.gguf b/Orca-2-13b-Q6_K.gguf new file mode 100644 index 0000000..0efd04d --- /dev/null +++ b/Orca-2-13b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487ba0037cc1d8c2b489818d1aef5bf1872874ce592b75e151685300140ea375 +size 10679165632 diff --git a/Orca-2-13b-Q8_0.gguf b/Orca-2-13b-Q8_0.gguf new file mode 100644 index 0000000..67ee4e9 --- /dev/null +++ b/Orca-2-13b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9860e2225d7983fcc1906d8ebb4a9bc43f45bd9ecb1263c017490c3ed4831287 +size 13831352256 diff --git a/Orca-2-13b-ggml-model-q4_0.gguf b/Orca-2-13b-ggml-model-q4_0.gguf new file mode 100644 index 0000000..3417cdd --- /dev/null +++ b/Orca-2-13b-ggml-model-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9ca393b2d882bd7bd0ba672d52eafa29bb22b2cd740418198c1fa1adb6478b +size 7365856000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a84c0e --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: microsoft/Orca-2-13b +inference: false +library_name: transformers +license: other +license_name: microsoft-research-license +license_link: LICENSE +model_creator: TinyLlama +model_name: Tinyllama 1.1B Chat v1.0 +model_type: tinyllama +tags: +- orca +- orca2 +- microsoft +pipeline_tag: text-generation +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Orca-2-13B-GGUF + +## Original Model + +[microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `chatml` + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {prompt}<|im_end|> + <|im_start|>assistant + ``` + +- Context size: `5120` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Orca-2-13b-Q5_K_M.gguf llama-api-server.wasm -p chatml + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Orca-2-13b-Q5_K_M.gguf llama-chat.wasm -p chatml + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Orca-2-13b-Q2_K.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q2_K.gguf) | Q2_K | 2 | 5.43 GB| smallest, significant quality loss - not recommended for most purposes | +| [Orca-2-13b-Q3_K_L.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| small, substantial quality loss | +| [Orca-2-13b-Q3_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| very small, high quality loss | +| [Orca-2-13b-Q3_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| very small, high quality loss | +| [Orca-2-13b-Q4_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Orca-2-13b-Q4_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| medium, balanced quality - recommended | +| [Orca-2-13b-Q4_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| small, greater quality loss | +| [Orca-2-13b-Q5_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Orca-2-13b-Q5_K_M.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| large, very low quality loss - recommended | +| [Orca-2-13b-Q5_K_S.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| large, low quality loss - recommended | +| [Orca-2-13b-Q6_K.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q6_K.gguf) | Q6_K | 6 | 10.7 GB| very large, extremely low quality loss | +| [Orca-2-13b-Q8_0.gguf](https://huggingface.co/second-state/Orca-2-13B-GGUF/blob/main/Orca-2-13b-Q8_0.gguf) | Q8_0 | 8 | 13.8 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..f0f2ea5 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.33.1", + "use_cache": true, + "vocab_size": 32003 +} 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