commit d8e963ee0af146cb35b6cf72fe86d293eb8ac3fa Author: ModelHub XC Date: Fri Jul 17 23:11:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/DeepSeek-V2-Lite-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0bfca52 --- /dev/null +++ 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-V2-Lite-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V2-Lite-Chat-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-V2-Lite-Chat-Q2_K.gguf b/DeepSeek-V2-Lite-Chat-Q2_K.gguf new file mode 100644 index 0000000..1bef9fd --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92df94f2f131ea5761bb454f6157303348142af258f93f9701d9f1db3758be75 +size 6430464320 diff --git a/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf b/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..864f3ad --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959d3d626a1888724b5df16fddd0ba69c6117e8326ed43d89b841817675f58e4 +size 8459398464 diff --git a/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf b/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..9c2bc2b --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c1b1c347222101f5bfce551c5ec6807cd81bcf0303b7c183948621dc4aa7d4 +size 8126606656 diff --git a/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf b/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..b752aa4 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54eb4c28d6a1e38d0c22392a3f269d1c37b09e07cd6328a30e76ce7bddccfc15 +size 7487663424 diff --git a/DeepSeek-V2-Lite-Chat-Q4_0.gguf b/DeepSeek-V2-Lite-Chat-Q4_0.gguf new file mode 100644 index 0000000..f66fc52 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526451466948e0a74158b43588bca6269bc46392d0c6689e98a011af7d412aaa +size 8905109824 diff --git a/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf b/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..940e294 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b4fb4ab1fbe1c6a827303ea898296c9faf8f54d6cdf8b9fbdda7a7ebfb292a +size 10364416320 diff --git a/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf b/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..1a8979d --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e8cde8c7f2baa606bc58d7470739a962113b94a75efaed10d626a071461f4e +size 9533608256 diff --git a/DeepSeek-V2-Lite-Chat-Q5_0.gguf b/DeepSeek-V2-Lite-Chat-Q5_0.gguf new file mode 100644 index 0000000..1310251 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fd631ce1222b84366dd75e2b0d5da3615747a9865f4a75eac965909d35c3c38 +size 10841764160 diff --git a/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf b/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..c273597 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76c60363eadb48c1fd3678b0dcbbabb39b959f336ae0c7c6e51396f6b18ad96 +size 11851313472 diff --git a/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf b/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..532fcaf --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b039106af0b8b68b678c27eb156b47375569a2eb4644b5adb58f368216a9070 +size 11143057728 diff --git a/DeepSeek-V2-Lite-Chat-Q6_K.gguf b/DeepSeek-V2-Lite-Chat-Q6_K.gguf new file mode 100644 index 0000000..f58de42 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232ec7dbfdb340d3ca020508b1e2e2791da2ae2baac21cf2f0491b781a314be1 +size 14066971968 diff --git a/DeepSeek-V2-Lite-Chat-Q8_0.gguf b/DeepSeek-V2-Lite-Chat-Q8_0.gguf new file mode 100644 index 0000000..26ced54 --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458d8dbb5c64109623751f3c7e691f285770a6521bf06bf86172980b995b3bde +size 16702517568 diff --git a/DeepSeek-V2-Lite-Chat-f16.gguf b/DeepSeek-V2-Lite-Chat-f16.gguf new file mode 100644 index 0000000..0d2498e --- /dev/null +++ b/DeepSeek-V2-Lite-Chat-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef9ac89c78b82e188cad8c75d0cb630899e08510a97d6fa41431139573f697c +size 31424033088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..196db21 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: deepseek-ai/DeepSeek-V2-Lite-Chat +inference: false +license: other +license_name: deepseek +license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL +model_creator: DeepSeek-ai +model_name: DeepSeek-V2-Lite-Chat +model_type: deepseek +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# DeepSeek-V2-Lite-Chat-GGUF + +## Original Model + +[deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat) + +## 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` + + + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [DeepSeek-V2-Lite-Chat-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q2_K.gguf) | Q2_K | 2 | 6.43 GB| smallest, significant quality loss - not recommended for most purposes | +| [DeepSeek-V2-Lite-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 8.46 GB| small, substantial quality loss | +| [DeepSeek-V2-Lite-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 8.13 GB| very small, high quality loss | +| [DeepSeek-V2-Lite-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 7.49 GB| very small, high quality loss | +| [DeepSeek-V2-Lite-Chat-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_0.gguf) | Q4_0 | 4 | 8.91 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [DeepSeek-V2-Lite-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 10.4 GB| medium, balanced quality - recommended | +| [DeepSeek-V2-Lite-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 9.53 GB| small, greater quality loss | +| [DeepSeek-V2-Lite-Chat-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_0.gguf) | Q5_0 | 5 | 10.8 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [DeepSeek-V2-Lite-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 11.9 GB| large, very low quality loss - recommended | +| [DeepSeek-V2-Lite-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 11.1 GB| large, low quality loss - recommended | +| [DeepSeek-V2-Lite-Chat-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q6_K.gguf) | Q6_K | 6 | 14.1 GB| very large, extremely low quality loss | +| [DeepSeek-V2-Lite-Chat-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q8_0.gguf) | Q8_0 | 8 | 16.7 GB| very large, extremely low quality loss - not recommended | +| [DeepSeek-V2-Lite-Chat-f16.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-f16.gguf) | f16 | 16 | 31.4 GB| | + +*Quatized with llama.cpp b3333* \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a1aa812 --- /dev/null +++ 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": "4.33.1", + "use_cache": true, + "v_head_dim": 128, + "vocab_size": 102400 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file