commit ac92dd7bd0582e72c4600008d383d227be67458e Author: ModelHub XC Date: Tue May 26 23:36:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Phi-3-mini-128k-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16e9def --- /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 +Phi-3-mini-128k-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-3-mini-128k-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-3-mini-128k-instruct-Q2_K.gguf b/Phi-3-mini-128k-instruct-Q2_K.gguf new file mode 100644 index 0000000..55859a6 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb79b6f11ddac3e4367266bc82c2a716f28aaf62c1da412514d67a1c17cc5503 +size 1416204256 diff --git a/Phi-3-mini-128k-instruct-Q3_K_L.gguf b/Phi-3-mini-128k-instruct-Q3_K_L.gguf new file mode 100644 index 0000000..3ab7c76 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233f408aceed4393cae648bf0b264393f66437ca2aad0105229dc2d9aafe6027 +size 2087597536 diff --git a/Phi-3-mini-128k-instruct-Q3_K_M.gguf b/Phi-3-mini-128k-instruct-Q3_K_M.gguf new file mode 100644 index 0000000..f10def5 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaafe463ed6071b0b1e60ea1887e676dc90c2c2c6e9201f3f18ac5784c9b850d +size 1955476960 diff --git a/Phi-3-mini-128k-instruct-Q3_K_S.gguf b/Phi-3-mini-128k-instruct-Q3_K_S.gguf new file mode 100644 index 0000000..eaca10b --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744bff1e726ccd26508ffa6e19603649d903e0f398d72af48e378f9f2e0f963b +size 1681798624 diff --git a/Phi-3-mini-128k-instruct-Q4_0.gguf b/Phi-3-mini-128k-instruct-Q4_0.gguf new file mode 100644 index 0000000..16bbf75 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d91369a18e1d61ebcb027ca4e390c2fdea072d1b26f00e8f3d81f8de76fcbc1 +size 2176177120 diff --git a/Phi-3-mini-128k-instruct-Q4_K_M.gguf b/Phi-3-mini-128k-instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a2534bb --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94c3dc9425904d90b768713b2be67d383d1f307b4913030cbb0ed47090a0f7ab +size 2393232352 diff --git a/Phi-3-mini-128k-instruct-Q4_K_S.gguf b/Phi-3-mini-128k-instruct-Q4_K_S.gguf new file mode 100644 index 0000000..9a85b4c --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:719fb06db51c0fcdb7c12d6e6e2a286d17144ee19a85abca892c3bda747aa285 +size 2188760032 diff --git a/Phi-3-mini-128k-instruct-Q5_0.gguf b/Phi-3-mini-128k-instruct-Q5_0.gguf new file mode 100644 index 0000000..2d02f07 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26b7566bc7c7783aa1f1588c603d508e5cbd15952ef896e0e8cf92f5239f62fa +size 2641474528 diff --git a/Phi-3-mini-128k-instruct-Q5_K_M.gguf b/Phi-3-mini-128k-instruct-Q5_K_M.gguf new file mode 100644 index 0000000..4db9229 --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b4371f288fb73d854e0798bbb64e532e9787919d9af793fe6c8bc4c878ef87 +size 2815276000 diff --git a/Phi-3-mini-128k-instruct-Q5_K_S.gguf b/Phi-3-mini-128k-instruct-Q5_K_S.gguf new file mode 100644 index 0000000..3fc371b --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65aec9bfd8154ca5d5417bc26e2851564d1e389b73b266b72f64481d61ee0b19 +size 2641474528 diff --git a/Phi-3-mini-128k-instruct-Q6_K.gguf b/Phi-3-mini-128k-instruct-Q6_K.gguf new file mode 100644 index 0000000..c5c1bdf --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be61c29a442e8a1e91b6385f550aee3ca22f309e4949aacd5e8fe63ddc299a1b +size 3135853024 diff --git a/Phi-3-mini-128k-instruct-Q8_0.gguf b/Phi-3-mini-128k-instruct-Q8_0.gguf new file mode 100644 index 0000000..d90499b --- /dev/null +++ b/Phi-3-mini-128k-instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b977fcd05546427229af675fc6a8ea2140f0cc20b1fb7e6aeb1dcaa758112017 +size 4061222368 diff --git a/Phi-3-mini-128k-instruct-f16.gguf b/Phi-3-mini-128k-instruct-f16.gguf new file mode 100644 index 0000000..896e0b8 --- /dev/null +++ b/Phi-3-mini-128k-instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce1208c5e84b3ab44af8faeb793ce2ea09923c79ea157225cd1b74044ee28a9 +size 7643297248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bcca625 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: microsoft/Phi-3-mini-128k-instruct +license: mit +license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE +language: +- en +pipeline_tag: text-generation +model_creator: Microsoft +model_name: Phi 3 mini 128k instruct +model_type: phi-msft +quantized_by: Second State Inc. +tags: +- nlp +- code +--- + + + +
+ +
+
+ + + +> [!CAUTION] +> The gguf models have been updated! The conversion is done with llama.cpp b3463. + + +# Phi-3-mini-128k-instruct-GGUF + +## Original Model + +[microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.12.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.2) and above + +- Prompt template + + - Prompt type: `phi-3-chat` + + - Prompt string + + ```text + <|system|> + {system_message}<|end|> + <|user|> + {user_message_1}<|end|> + <|assistant|> + {assistant_message_1}<|end|> + <|user|> + {user_message_2}<|end|> + <|assistant|> + ``` + +- Context size: `128000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-128k-instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template phi-3-chat \ + --ctx-size 128000 \ + --model-name phi-3-mini-128k + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-128k-instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template phi-3-chat \ + --ctx-size 128000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Phi-3-mini-128k-instruct-Q2_K.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q2_K.gguf) | Q2_K | 2 | 1.42 GB| smallest, significant quality loss - not recommended for most purposes | +| [Phi-3-mini-128k-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.09 GB| small, substantial quality loss | +| [Phi-3-mini-128k-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.96 GB| very small, high quality loss | +| [Phi-3-mini-128k-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.68 GB| very small, high quality loss | +| [Phi-3-mini-128k-instruct-Q4_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_0.gguf) | Q4_0 | 4 | 2.18 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Phi-3-mini-128k-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.39 GB| medium, balanced quality - recommended | +| [Phi-3-mini-128k-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.19 GB| small, greater quality loss | +| [Phi-3-mini-128k-instruct-Q5_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_0.gguf) | Q5_0 | 5 | 2.64 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Phi-3-mini-128k-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.82 GB| large, very low quality loss - recommended | +| [Phi-3-mini-128k-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.64 GB| large, low quality loss - recommended | +| [Phi-3-mini-128k-instruct-Q6_K.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q6_K.gguf) | Q6_K | 6 | 3.14 GB| very large, extremely low quality loss | +| [Phi-3-mini-128k-instruct-Q8_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q8_0.gguf) | Q8_0 | 8 | 4.06 GB| very large, extremely low quality loss - not recommended | +| [Phi-3-mini-128k-instruct-f16.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-f16.gguf) | f16 | 16 | 7.64 GB| | + +*Quantized with llama.cpp b3463.* diff --git a/config.json b/config.json new file mode 100644 index 0000000..a6e648f --- /dev/null +++ b/config.json @@ -0,0 +1,137 @@ +{ + "_name_or_path": "Phi-3-mini-128k-instruct", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM" + }, + "bos_token_id": 1, + "embd_pdrop": 0.0, + "eos_token_id": 32000, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "model_type": "phi3", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "original_max_position_embeddings": 4096, + "pad_token_id": 32000, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1.0299999713897705, + 1.0499999523162842, + 1.0499999523162842, + 1.0799999237060547, + 1.2299998998641968, + 1.2299998998641968, + 1.2999999523162842, + 1.4499999284744263, + 1.5999999046325684, + 1.6499998569488525, + 1.8999998569488525, + 2.859999895095825, + 3.68999981880188, + 5.419999599456787, + 5.489999771118164, + 5.489999771118164, + 9.09000015258789, + 11.579999923706055, + 15.65999984741211, + 15.769999504089355, + 15.789999961853027, + 18.360000610351562, + 21.989999771118164, + 23.079999923706055, + 30.009998321533203, + 32.35000228881836, + 32.590003967285156, + 35.56000518798828, + 39.95000457763672, + 53.840003967285156, + 56.20000457763672, + 57.95000457763672, + 59.29000473022461, + 59.77000427246094, + 59.920005798339844, + 61.190006256103516, + 61.96000671386719, + 62.50000762939453, + 63.3700065612793, + 63.48000717163086, + 63.48000717163086, + 63.66000747680664, + 63.850006103515625, + 64.08000946044922, + 64.760009765625, + 64.80001068115234, + 64.81001281738281, + 64.81001281738281 + ], + "short_factor": [ + 1.05, + 1.05, + 1.05, + 1.1, + 1.1, + 1.1500000000000001, + 1.2000000000000002, + 1.2500000000000002, + 1.3000000000000003, + 1.3500000000000003, + 1.5000000000000004, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.000000000000001, + 2.0500000000000007, + 2.0500000000000007, + 2.0500000000000007, + 2.1000000000000005, + 2.1000000000000005, + 2.1000000000000005, + 2.1500000000000004, + 2.1500000000000004, + 2.3499999999999996, + 2.549999999999999, + 2.5999999999999988, + 2.5999999999999988, + 2.7499999999999982, + 2.849999999999998, + 2.849999999999998, + 2.9499999999999975 + ], + "type": "su" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.39.3", + "use_cache": true, + "vocab_size": 32064 +} 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