初始化项目，由ModelHub XC社区提供模型

Model: second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF Source: Original Platform
2026-09-18 22:10:17 +08:00
commit b715ca8384
16 changed files with 197 additions and 0 deletions
--- a/.gitattributes
+++ 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
+DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def5f628be356d6d4c92913c4ab227d34972e79398e4c304988d28f4e70213af
+size 3015939776
--- a/DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc64f6812c551f85ba7a0a0de222337223df4d424b377ae4f2297209d860a34
+size 4088458944
--- a/DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd1331f4087879c4bc2a0443526ea8a97d807abe1654328f68629ff426c9bae
+size 3808390848
--- a/DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54cda95194bfcaef6176e508fc0c1a92af368bf6d30049da2f65634f6c372b2b
+size 3492368064
--- a/DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f1ec848ae1c65578105d1ef880a291390edc0c6d07c7ec1734a9f753d65ad9
+size 4431390400
--- a/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eda5f18e3b32782f053c4baefa363a96b390cbab6f9fe643d9cec478898b36a
+size 4683073216
--- a/DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c251f553b060c206c9b0bde01253c08bdb78e84b5b213f7d1dac41f2a927ef5
+size 4457768640
--- a/DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11585d590f930de302009d65675c8a30ce0f27be6f1878a78ffa1b5429ef8228
+size 5315176128
--- a/DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0366f3aed111846266153192edcd90dfcd39ae374f6d07fa243c8acc46041f16
+size 5444830912
--- a/DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab3f7a9efcc79055542c51418960aa3fdaf4ca11dd17ea2ba2fafdbae724f062
+size 5315176128
--- a/DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f9c8008ed93e268f9f635e51726e6ce58ff4f861724903b1fb61ff25aab1ab
+size 6254198464
--- a/DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf965fadac9d87c26a2d102ec90c45439c0c8a8c0c1f23f2e72c461014df8b9c
+size 8098524864
--- a/DeepSeek-R1-Distill-Qwen-7B-f16.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3800f07f3ca5a96897aaf46892105cb03bc9f8a29b1cdf20122beb0cd018815
+size 15237852864
--- a/README.md
+++ b/README.md
@@ -0,0 +1,82 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+license: apache-2.0
+license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/LICENSE
+model_creator: deepseek-ai
+model_name: DeepSeek-R1-Distill-Qwen-7B
+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-Distill-Qwen-7B-GGUF
+
+## Original Model
+
+[deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8)
+
+- 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-Distill-Qwen-7B-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name DeepSeek-R1-Distill-Qwen-7B \
+    --prompt-template chatml \
+    --ctx-size 128000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-Distill-Qwen-7B-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-Distill-Qwen-7B-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q2_K.gguf)     | Q2_K   | 2 | 3.02 GB| smallest, significant quality loss - not recommended for most purposes |
+| [DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
+| [DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
+| [DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
+| [DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q4_0.gguf)     | Q4_0   | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
+| [DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
+| [DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q5_0.gguf)     | Q5_0   | 5 | 5.32 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
+| [DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.32 GB| large, low quality loss - recommended |
+| [DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q6_K.gguf)     | Q6_K   | 6 | 6.25 GB| very large, extremely low quality loss |
+| [DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-Q8_0.gguf)     | Q8_0   | 8 | 8.21 GB| very large, extremely low quality loss - not recommended |
+| [DeepSeek-R1-Distill-Qwen-7B-f16.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Qwen-7B-GGUF/blob/main/DeepSeek-R1-Distill-Qwen-7B-f16.gguf)       | f16    | 16 | 15.2 GB| |
+
+*Quantized with llama.cpp b4519*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}