初始化项目，由ModelHub XC社区提供模型

Model: second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF Source: Original Platform
2026-07-18 03:48:07 +08:00
commit afc2af1536
17 changed files with 235 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-Coder-V2-Lite-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4eb2f3365ac103d4231352b331577135be67931cecedad474c38e4cecb9182d
+size 6430464480
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9b1b46859bb2208acf2174192547e53389575fb2af820a988c91ecb94c2613
+size 8459398624
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3918c980cc193aa63733db160fdd26ef3a668fecd5219d0e1aa62d12c86cc91f
+size 8126606816
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15476c1c838f3a8205d0d7725a1f2b377da0ba1c287149680dbffc8d755904d2
+size 7487663584
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q4_0.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d932d742f5e09b66cf017bb0e27bf5acf1d0a12d0e65bcc4561528020c4b56c
+size 8905109984
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc76f3326b49b4d81d1027d092bf7ce5b4ed2de4136d1d2e7e6347c3ec8376
+size 10364416480
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a9e203ee6f5ed208c4d8859b7c2c2914bd1af8621d90f366dd7b0bd9112d5c
+size 9533608416
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q5_0.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd09a611559c2f97767a41e555dd05d0c6a61425bf14d2d1e2cf0ea817690dd
+size 10841764320
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b4ff12b045ec0001a690249931d91acbcbe007694352d6ac5bf86e16f6fc6b
+size 11851313632
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03f2eacb23d597e7793a57bcaabcc3ebceec1515b04a0fe49996817ff169922d
+size 11143057888
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cfe5211943fffec745261aba45023b07d1a9004356a4efdfbf855bf47ca6782
+size 14066972128
--- a/DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373dcfc92e01372709b6164fc836f677a6280e25e9eac5c434c64223207bfc4f
+size 16702517728
--- a/DeepSeek-Coder-V2-Lite-Instruct-f16.gguf
+++ b/DeepSeek-Coder-V2-Lite-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de57aa898372715c457b7c06362bb9826f3e47ba2a83679f162fcb7b40e763b
+size 31424033248
--- a/README.md
+++ b/README.md
@@ -0,0 +1,88 @@
+---
+base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
+inference: false
+license: other
+license_name: deepseek-license
+license_link: LICENSE
+model_creator: DeepSeek-ai
+model_name: DeepSeek-Coder-V2-Lite-Instruct
+model_type: deepseek
+quantized_by: Second State Inc.
+---
+
+<!-- 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-Coder-V2-Lite-Instruct-GGUF
+
+## Original Model
+
+[deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.12.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.3) and above
+
+- Prompt template
+
+  - Prompt type: `deepseek-chat-2`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_sentence|>{system_message}
+
+    User: {user_message_1}
+
+    Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}
+
+    Assistant:
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template deepseek-chat-2 \
+    --ctx-size 128000 \
+    --model-name DeepSeek-Coder-V2-Lite-Instruct
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template deepseek-chat-2 \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 6.43 GB| smallest, significant quality loss - not recommended for most purposes |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 8.46 GB| small, substantial quality loss |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 8.13 GB| very small, high quality loss |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 7.49 GB| very small, high quality loss |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 8.91 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 10.4 GB| medium, balanced quality - recommended |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 9.53 GB| small, greater quality loss |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 10.8 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 11.9 GB| large, very low quality loss - recommended |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 11.1 GB| large, low quality loss - recommended |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 14.1 GB| very large, extremely low quality loss |
+| [DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 16.7 GB| very large, extremely low quality loss - not recommended |
+| [DeepSeek-Coder-V2-Lite-Instruct-f16.gguf](https://huggingface.co/second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-f16.gguf)     | f16    | 16 | 31.4 GB| |
+
+*Quatized with llama.cpp b3212*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_deepseek.DeepseekV2Config",
+    "AutoModel": "modeling_deepseek.DeepseekV2Model",
+    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+  },
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "first_k_dense_replace": 1,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 163840,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": false,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 40,
+    "mscale": 0.707,
+    "mscale_all_dim": 0.707,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000,
+  "routed_scaling_factor": 1.0,
+  "scoring_func": "softmax",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "greedy",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "v_head_dim": 128,
+  "vocab_size": 102400
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`