初始化项目，由ModelHub XC社区提供模型

Model: second-state/DeepSeek-R1-0528-Qwen3-8B-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
+DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-0528-Qwen3-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text

DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fc75a769499536be3cde6c6ab0933cd1420c129b1026779bd01c0391ab6ee8
+size 3281731648

DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426fc73836e4af4dd37a00323a860ece84442d50ae0a065c89ce11f2e577091b
+size 4431392832

DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ba34e7dee2305e1057348cf6aa22e9cf7f0706084f63a15ba94add1229274f
+size 4124160064

DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6fe5bf7a7cefafef63a0badd14232073cc305c656819dd989523bb5746b5bf
+size 3769610304

DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a12250cdeac408bdc0edeef69facafb2372c152a5280afecc8c0153c2dfb34
+size 4774748224

DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21927de884a9335f661a587b391fe63c2ae5ccbbce7b9054f437ef7dd80c686f
+size 5027782720

DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6dd8f02e59c8de971424667a697062713275933481b33fbff94fcffecc01ef
+size 4802011200

DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bccc0cbd303a87f3f609fae9a307ccc19e45384ac3cc5581d2579573ee545b
+size 5720760384

DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a01af1ab3c85334f0b3e10292659d0f0f18cb5154f59674e811bfd39cd0174
+size 5851111488

DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ca8a80a8b07efb8fce84aab3c56decc9824be28220319fbe01478c715274da
+size 5720760384

DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2913106b493ae31f79ce30f1bd0093ce69a4ac048f54f44d3827fefa97897f5c
+size 6725898304

DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c653bcb35f43a470c360364a08d6531ca671bf152527164a353f9ac8052abd
+size 8709517376

DeepSeek-R1-0528-Qwen3-8B-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c5da368c781ba65788b7e5a888cb53e77e2c37b69059bd6316e7eb101164a9
+size 16388042816

README.md

@@ -0,0 +1,81 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
+license: mit
+model_creator: deepseek-ai
+model_name: DeepSeek-R1-0528-Qwen3-8B
+quantized_by: Second State Inc.
+library_name: transformers
+---
+
+<!-- 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 -->
+
+# DeepSeek-R1-0528-Qwen3-8B-GGUF
+
+## Original Model
+
+[deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.21.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.21.0) or 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: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name DeepSeek-R1-0528-Qwen3-8B \
+    --prompt-template chatml \
+    --ctx-size 128000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf)     | Q2_K   | 2 | 3.28 GB| smallest, significant quality loss - not recommended for most purposes |
+| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.43 GB| small, substantial quality loss |
+| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.12 GB| very small, high quality loss |
+| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.77 GB| very small, high quality loss |
+| [DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf)     | Q4_0   | 4 | 4.77 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf) | Q4_K_M | 4 | 5.03 GB| medium, balanced quality - recommended |
+| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.80 GB| small, greater quality loss |
+| [DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf)     | Q5_0   | 5 | 5.72 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.85 GB| large, very low quality loss - recommended |
+| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.72 GB| large, low quality loss - recommended |
+| [DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf)     | Q6_K   | 6 | 6.73 GB| very large, extremely low quality loss |
+| [DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf)     | Q8_0   | 8 | 8.71 GB| very large, extremely low quality loss - not recommended |
+| [DeepSeek-R1-0528-Qwen3-8B-f16.gguf](https://huggingface.co/second-state/DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-f16.gguf)       | f16    | 16 | 16.4 GB| |
+
+*Quantized with llama.cpp b5501*

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "rope_type": "yarn",
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "attn_factor": 0.8782488562869419
+  },
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}