初始化项目，由ModelHub XC社区提供模型

Model: second-state/Phi-3-medium-4k-instruct-GGUF
Source: Original Platform

.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-medium-4k-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3-medium-4k-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

Phi-3-medium-4k-instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5584d5e850801c4f32fee2b1171c05eaa1f9925889555b3c83eda9970a20c7
+size 5142999648

Phi-3-medium-4k-instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa511d6c9c7f29b6fccd2fa7c80374396fbd72fda096dcc551ac358b8d1d377
+size 7490296928

Phi-3-medium-4k-instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:314bce75c1425616d504fe1bb9a891a29541d56d11b2763aa50932d7b6ac1f00
+size 6923410528

Phi-3-medium-4k-instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66067b17b01c6571de933bb34cfe6c99745c0495821119e0b6f4a47e6fbf6a8
+size 6064888928

Phi-3-medium-4k-instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeeec065542176eb30cfb3594faf069cddd93220d1faa23c39dac45d6debfef
+size 7897124448

Phi-3-medium-4k-instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f74f6ffa9b019f43f05677d73f357aa8bbebdb2b6ecc3e9f19443c6c4c654982
+size 8566820448

Phi-3-medium-4k-instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c37a6c54c6e36d90bff62b9da4dc339bcf9335585a1364cf361d74d742b6de
+size 7954468448

Phi-3-medium-4k-instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f445433d2fd906728a55ef87a32bce680145a47f0f0a37dfd6d5964475507b
+size 9621581408

Phi-3-medium-4k-instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a6cbc460f21a6d43ea4c21e177c24db566bff26206e012d700c91798819c21
+size 10074189408

Phi-3-medium-4k-instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f50b1c4d9fa3085a67d0d567f75a1dd8982389f733c7af2351ab18487697bd3
+size 9621581408

Phi-3-medium-4k-instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77798707e52b68647f84675b3d7ba673d36616d19f7b5b5b3de65dff5c072da
+size 11453816928

Phi-3-medium-4k-instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27751464b5a6cccc2eae0efefd443aca688fc911fb9a52948798b83ad2c90150
+size 14834711648

Phi-3-medium-4k-instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a8dedc7dfd08a58fb06d4066b9822f434d356681bd51dbe5c8c1489e892399
+size 27922046048

README.md

@@ -0,0 +1,92 @@
+---
+base_model: microsoft/Phi-3-medium-4k-instruct
+license: mit
+license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
+language:
+- multilingual
+pipeline_tag: text-generation
+model_creator: Microsoft
+model_name: Phi 3 medium 4k instruct
+model_type: phi-msft
+quantized_by: Second State Inc.
+tags:
+- nlp
+- code
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Phi-3-medium-4k-instruct-GGUF
+
+## Original Model
+
+[microsoft/Phi-3-medium-4k-instruct](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2) 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: `4000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-medium-4k-instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template phi-3-chat \
+    --ctx-size 4000 \
+    --model-name phi-3-medium-4k
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-medium-4k-instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template phi-3-chat \
+    --ctx-size 4000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Phi-3-medium-4k-instruct-Q2_K.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q2_K.gguf)     | Q2_K   | 2 | 5.14 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Phi-3-medium-4k-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.49 GB| small, substantial quality loss |
+| [Phi-3-medium-4k-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 6.92 GB| very small, high quality loss |
+| [Phi-3-medium-4k-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 6.06 GB| very small, high quality loss |
+| [Phi-3-medium-4k-instruct-Q4_0.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_0.gguf)     | Q4_0   | 4 | 7.9 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Phi-3-medium-4k-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 8.57 GB| medium, balanced quality - recommended |
+| [Phi-3-medium-4k-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 7.95 GB| small, greater quality loss |
+| [Phi-3-medium-4k-instruct-Q5_0.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_0.gguf)     | Q5_0   | 5 | 9.62 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Phi-3-medium-4k-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 10.1 GB| large, very low quality loss - recommended |
+| [Phi-3-medium-4k-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 9.62 GB| large, low quality loss - recommended |
+| [Phi-3-medium-4k-instruct-Q6_K.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q6_K.gguf)     | Q6_K   | 6 | 11.5 GB| very large, extremely low quality loss |
+| [Phi-3-medium-4k-instruct-Q8_0.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q8_0.gguf)     | Q8_0   | 8 | 14.8 GB| very large, extremely low quality loss - not recommended |
+| [Phi-3-medium-4k-instruct-f16.gguf](https://huggingface.co/second-state/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-f16.gguf)     | f16   | 16 | 27.9 GB|  |
+
+*Quantized with llama.cpp b2961.*

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Phi-3-medium-4k-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": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 32064
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}