commit 5980dcd2b5f531ab6b794ab5fc420a87508cb91c Author: ModelHub XC Date: Wed Aug 26 17:48:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Phi-4-mini-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..974c24d --- /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-4-mini-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-4-mini-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-4-mini-instruct-Q2_K.gguf b/Phi-4-mini-instruct-Q2_K.gguf new file mode 100644 index 0000000..7fdc1b7 --- /dev/null +++ b/Phi-4-mini-instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295c3972f54c20a47d571495f167db7e02c4981207f03e51d5c00479a374f3b3 +size 1682636096 diff --git a/Phi-4-mini-instruct-Q3_K_L.gguf b/Phi-4-mini-instruct-Q3_K_L.gguf new file mode 100644 index 0000000..f5eea33 --- /dev/null +++ b/Phi-4-mini-instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cc1941ccad9f14c987b4ec12cab07c5312de6dec46dc5dd8b45170675c7698 +size 2249653568 diff --git a/Phi-4-mini-instruct-Q3_K_M.gguf b/Phi-4-mini-instruct-Q3_K_M.gguf new file mode 100644 index 0000000..0e6ceb0 --- /dev/null +++ b/Phi-4-mini-instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e0aae476fc464b8635c08fe50f355e3f096b98328fe520073800c4b211bdbc +size 2117532992 diff --git a/Phi-4-mini-instruct-Q3_K_S.gguf b/Phi-4-mini-instruct-Q3_K_S.gguf new file mode 100644 index 0000000..be42e20 --- /dev/null +++ b/Phi-4-mini-instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3392e587db39e5efd86812484b4f09ea84f43324b8dafd9741434404928819fa +size 1897332032 diff --git a/Phi-4-mini-instruct-Q4_0.gguf b/Phi-4-mini-instruct-Q4_0.gguf new file mode 100644 index 0000000..0e6e547 --- /dev/null +++ b/Phi-4-mini-instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59eb0cc05b6af62a240c6ef0b9c755920b729d85bc7bbee354b2511cadf9bc95 +size 2325151040 diff --git a/Phi-4-mini-instruct-Q4_K_M.gguf b/Phi-4-mini-instruct-Q4_K_M.gguf new file mode 100644 index 0000000..d93aa55 --- /dev/null +++ b/Phi-4-mini-instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55239fbd0dc947146be056e7850d2fa3a55d0091aa2cc873767e686c3b15eeed +size 2491874624 diff --git a/Phi-4-mini-instruct-Q4_K_S.gguf b/Phi-4-mini-instruct-Q4_K_S.gguf new file mode 100644 index 0000000..cc9d4c4 --- /dev/null +++ b/Phi-4-mini-instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332b24022d5f2343897b18ea33c23fce7b44682620bc7667f05ab76a10690bd8 +size 2337733952 diff --git a/Phi-4-mini-instruct-Q5_0.gguf b/Phi-4-mini-instruct-Q5_0.gguf new file mode 100644 index 0000000..1ebeaf0 --- /dev/null +++ b/Phi-4-mini-instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1d2c9f4cb7a11e908d5d6bd8e07f3ea26f9228a8b38f61ddc819a86d1501eb +size 2727804224 diff --git a/Phi-4-mini-instruct-Q5_K_M.gguf b/Phi-4-mini-instruct-Q5_K_M.gguf new file mode 100644 index 0000000..71c4c15 --- /dev/null +++ b/Phi-4-mini-instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e7555f68a3762f25ebba4acaac7f303979aa88eebf862f1f8a561103c9af70 +size 2848128320 diff --git a/Phi-4-mini-instruct-Q5_K_S.gguf b/Phi-4-mini-instruct-Q5_K_S.gguf new file mode 100644 index 0000000..c3bf5d2 --- /dev/null +++ b/Phi-4-mini-instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b258b9e38595ff3960657bf789e2de8651b0b60cfa36a6cef9a4d17a7734a0dc +size 2727804224 diff --git a/Phi-4-mini-instruct-Q6_K.gguf b/Phi-4-mini-instruct-Q6_K.gguf new file mode 100644 index 0000000..e0ed249 --- /dev/null +++ b/Phi-4-mini-instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172f36acd48986a382d78d98d6816f767c791e926a02bf7ac541e7cf58b51c28 +size 3155623232 diff --git a/Phi-4-mini-instruct-Q8_0.gguf b/Phi-4-mini-instruct-Q8_0.gguf new file mode 100644 index 0000000..2b78d48 --- /dev/null +++ b/Phi-4-mini-instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f3992305494d7d61267924a357f6d0f9e68035a38aa589cff386c09ee52bc9 +size 4084611392 diff --git a/Phi-4-mini-instruct-f16.gguf b/Phi-4-mini-instruct-f16.gguf new file mode 100644 index 0000000..6796024 --- /dev/null +++ b/Phi-4-mini-instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bb32183dad1cc57730edf523bd6ac18716005bb579384d279e029e63828f97 +size 7680694592 diff --git a/README.md b/README.md new file mode 100644 index 0000000..71a4510 --- /dev/null +++ b/README.md @@ -0,0 +1,111 @@ +--- +base_model: microsoft/Phi-4-mini-instruct +license: mit +license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct/resolve/main/LICENSE +language: +- "multilingual" +- "ar" +- "zh" +- "cs" +- "da" +- "nl" +- "en" +- "fi" +- "fr" +- "de" +- "he" +- "hu" +- "it" +- "ja" +- "ko" +- "no" +- "pl" +- "pt" +- "ru" +- "es" +- "sv" +- "th" +- "tr" +- "uk" +pipeline_tag: text-generation +library_name: transformers +model_creator: Microsoft +model_name: Phi-4-mini-instruct +quantized_by: Second State Inc. +tags: +- nlp +- code +--- + + + +
+ +
+
+ + +# Phi-4-mini-instruct-GGUF + +## Original Model + +[microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.16.9](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.9) and above + +- Prompt template + + - Prompt type: `phi-4-chat` + + - Prompt string + + ```text + <|im_start|>system<|im_sep|> + {system_message}<|im_end|> + <|im_start|>user<|im_sep|> + {user_message}<|im_end|> + <|im_start|>assistant<|im_sep|> + ``` + +- Context size: `128000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template phi-4-chat \ + --ctx-size 128000 \ + --model-name phi-4-mini + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template phi-4-chat \ + --ctx-size 128000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Phi-4-mini-instruct-Q2_K.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q2_K.gguf) | Q2_K | 2 | 1.68 GB| smallest, significant quality loss - not recommended for most purposes | +| [Phi-4-mini-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.25 GB| small, substantial quality loss | +| [Phi-4-mini-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 2.12 GB| very small, high quality loss | +| [Phi-4-mini-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.90 GB| very small, high quality loss | +| [Phi-4-mini-instruct-Q4_0.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_0.gguf) | Q4_0 | 4 | 2.33 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Phi-4-mini-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.49 GB| medium, balanced quality - recommended | +| [Phi-4-mini-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.34 GB| small, greater quality loss | +| [Phi-4-mini-instruct-Q5_0.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_0.gguf) | Q5_0 | 5 | 2.73 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Phi-4-mini-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.85 GB| large, very low quality loss - recommended | +| [Phi-4-mini-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.73 GB| large, low quality loss - recommended | +| [Phi-4-mini-instruct-Q6_K.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q6_K.gguf) | Q6_K | 6 | 3.16 GB| very large, extremely low quality loss | +| [Phi-4-mini-instruct-Q8_0.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-Q8_0.gguf) | Q8_0 | 8 | 4.08 GB| very large, extremely low quality loss - not recommended | +| [Phi-4-mini-instruct-f16.gguf](https://huggingface.co/second-state/Phi-4-mini-instruct-GGUF/blob/main/Phi-4-mini-instruct-f16.gguf) | f16 | 16 | 7.68 GB| | + +*Quantized with llama.cpp b4792.* diff --git a/config.json b/config.json new file mode 100644 index 0000000..679e70d --- /dev/null +++ b/config.json @@ -0,0 +1,144 @@ +{ + "_name_or_path": "Phi-4-mini-instruct", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_phi3.Phi3Config", + "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM", + "AutoTokenizer": "Xenova/gpt-4o" + }, + "bos_token_id": 199999, + "embd_pdrop": 0.0, + "eos_token_id": 199999, + "full_attn_mod": 1, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "interpolate_factor": 1, + "lm_head_bias": false, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "phi3", + "num_attention_heads": 24, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "original_max_position_embeddings": 4096, + "pad_token_id": 199999, + "partial_rotary_factor": 0.75, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "long_factor": [ + 1, + 1.118320672, + 1.250641126, + 1.398617824, + 1.564103225, + 1.74916897, + 1.956131817, + 2.187582649, + 2.446418898, + 2.735880826, + 3.059592084, + 3.421605075, + 3.826451687, + 4.279200023, + 4.785517845, + 5.351743533, + 5.984965424, + 6.693110555, + 7.485043894, + 8.370679318, + 9.36110372, + 10.4687158, + 11.70738129, + 13.09260651, + 14.64173252, + 16.37415215, + 18.31155283, + 20.47818807, + 22.90118105, + 25.61086418, + 28.64115884, + 32.03, + 32.1, + 32.13, + 32.23, + 32.6, + 32.61, + 32.64, + 32.66, + 32.7, + 32.71, + 32.93, + 32.97, + 33.28, + 33.49, + 33.5, + 44.16, + 47.77 + ], + "short_factor": [ + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0, + 1.0 + ], + "type": "longrope" + }, + "rope_theta": 10000.0, + "sliding_window": 262144, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.45.0", + "use_cache": true, + "vocab_size": 200064 +}