初始化项目，由ModelHub XC社区提供模型

Model: second-state/DeepSeek-R1-Distill-Llama-8B-GGUF Source: Original Platform
2026-08-06 19:41:17 +08:00
commit e2bf30c335
16 changed files with 205 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-Llama-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Llama-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b1b2b07a9bb8801524701652694d4f273c57761b82be8d31fdfc98cfd264fe
+size 3179133504
--- a/DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0312933e1c8e0335f19fb6d2abd160644cbe16877430540c29f1e878845683ed
+size 4321958464
--- a/DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed7e9d857c304751bbff087f5d5b311d2b64c864069177dbbe2797847f6ad22
+size 4018920000
--- a/DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f438fc4b8c091a1d1ccd0adec4cf70501f4596bc01fd76e103d03e42d62c0ed
+size 3664501312
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeff9a33ab8ad47a72e10193f5f60f559f6638f68cc61d8d12a6cf6ce6a3e63
+size 4661213760
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f903c95b79bc959ddc9ddf72622028540948fe8b53a3eb85a3e019a442287d93
+size 4920736320
--- a/DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a3b33cd3f933f76d02b736d83af7ea82c38a03b0c978ebc49230dd651d6324
+size 4692671040
--- a/DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0ad8d4ab9ef3fffa7e9e3b48e072ac13a612d66f2df5c4c62353d351036350
+size 5599296064
--- a/DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9627906af24eeece3929ab7c53fd6846e3dcb2fa9d25a411d1aa26e1fa5bc298
+size 5732989504
--- a/DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6e4da9d2cc75acf2a984ee09721b0c4c28b6753387b04f49194db2a5ea37cd
+size 5599296064
--- a/DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c2bf9131e7764a365e52614fc4981acbf5ae766e9e60e46c83a3a0f9d15c14
+size 6596008512
--- a/DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf976b94cb574b59fd618f1785a44f653b84659173dc258da63d5e2ca7ac038
+size 8540772928
--- a/DeepSeek-R1-Distill-Llama-8B-f16.gguf
+++ b/DeepSeek-R1-Distill-Llama-8B-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7889900cea3d7e3f9c71b632ba502d51a27de58fa0fe5804e596ee199c5f28be
+size 16068893248
--- a/README.md
+++ b/README.md
@@ -0,0 +1,84 @@
+---
+model_name: DeepSeek-R1-Distill-Llama-8B
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+model_creator: deepseek-ai
+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-Llama-8B-GGUF
+
+## Original Model
+
+[deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.16.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.8)
+
+- Prompt template
+
+  - Prompt type: `llama-3-chat`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+  
+    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 128000 \
+    --model-name DeepSeek-R1-Distill-Llama-8B
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q5_0.gguf)     | Q5_0   | 5 | 5.60 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.60 GB| large, low quality loss - recommended |
+| [DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q6_K.gguf)     | Q6_K   | 6 | 6.60 GB| very large, extremely low quality loss |
+| [DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [DeepSeek-R1-Distill-Llama-8B-f16.gguf](https://huggingface.co/second-state/DeepSeek-R1-Distill-Llama-8B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-8B-f16.gguf)       | f16    | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b4519*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}