commit 0bbd530120b96629f683e3e0a0406e9f9d5de3c7 Author: ModelHub XC Date: Tue May 26 23:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Yi-1.5-9B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9029ee7 --- /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 +Yi-1.5-9B-Chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Yi-1.5-9B-Chat-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..48fa2a4 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: 01-ai/Yi-1.5-9B-Chat +inference: false +model_creator: 01-ai +model_name: Yi-1.5-9B-Chat +model_type: yi +pipeline_tag: text-generation +quantized_by: Second State Inc. +license: apache-2.0 +--- + + + +
+ +
+
+ + +# Yi-1.5-9B-Chat-GGUF + +## Original Model + +[01-ai/Yi-1.5-9B-Chat](https://huggingface.co/01-ai/Yi-1.5-9B-Chat) + +## Run with LlamaEdge + + + +- LlamaEdge version: coming soon + +- Prompt template + + - Prompt type: `chatml` + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {prompt}<|im_end|> + <|im_start|>assistant + ``` + + - Reverse prompt: `<|im_end|>` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template chatml \ + --reverse-prompt "<|im_end|>" \ + --ctx-size 4096 \ + --model-name Yi-1.5-9B-Chat + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --reverse-prompt "<|im_end|>" \ + --ctx-size 4096 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Yi-1.5-9B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q2_K.gguf) | Q2_K | 2 | 3.35 GB| smallest, significant quality loss - not recommended for most purposes | +| [Yi-1.5-9B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 4.69 GB| small, substantial quality loss | +| [Yi-1.5-9B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 4.32 GB| very small, high quality loss | +| [Yi-1.5-9B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 3.9 GB| very small, high quality loss | +| [Yi-1.5-9B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_0.gguf) | Q4_0 | 4 | 5.04 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Yi-1.5-9B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 5.33 GB| medium, balanced quality - recommended | +| [Yi-1.5-9B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 5.07 GB| small, greater quality loss | +| [Yi-1.5-9B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_0.gguf) | Q5_0 | 5 | 6.11 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Yi-1.5-9B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 6.26 GB| large, very low quality loss - recommended | +| [Yi-1.5-9B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 6.11 GB| large, low quality loss - recommended | +| [Yi-1.5-9B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q6_K.gguf) | Q6_K | 6 | 7.25 GB| very large, extremely low quality loss | +| [Yi-1.5-9B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q8_0.gguf) | Q8_0 | 8 | 9.38 GB| very large, extremely low quality loss - not recommended | +| [Yi-1.5-9B-Chat-f16.gguf](https://huggingface.co/second-state/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-f16.gguf) | f16 | 16 | 17.7 GB| | + +*Quantized with llama.cpp b3135* diff --git a/Yi-1.5-9B-Chat-Q2_K.gguf b/Yi-1.5-9B-Chat-Q2_K.gguf new file mode 100644 index 0000000..4bba734 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2896e5ce9415e59250d9df8f59708673bdcc43fe4b8f666842b0b3ff93e5c096 +size 3354325344 diff --git a/Yi-1.5-9B-Chat-Q3_K_L.gguf b/Yi-1.5-9B-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..4d96d5e --- /dev/null +++ b/Yi-1.5-9B-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1f63912600ddcfa776adf4e42943923989718917e625c6f60459af2185c56f +size 4690751840 diff --git a/Yi-1.5-9B-Chat-Q3_K_M.gguf b/Yi-1.5-9B-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..d579d91 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20d8a088375cc4d4d836a0d58c8f828b2b014c666086c012c96aea81921d2707 +size 4324405600 diff --git a/Yi-1.5-9B-Chat-Q3_K_S.gguf b/Yi-1.5-9B-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..12d3253 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1ce41b06ed1edb3602ab0959c4b7a67293ae24fcb8ec45d89ea49a69dd01b2 +size 3899208032 diff --git a/Yi-1.5-9B-Chat-Q4_0.gguf b/Yi-1.5-9B-Chat-Q4_0.gguf new file mode 100644 index 0000000..53ba704 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c38cf69949b745d1e6ac6c517865bc3b75bf469a5850c5a8da608c4f226308 +size 5036994912 diff --git a/Yi-1.5-9B-Chat-Q4_K_M.gguf b/Yi-1.5-9B-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..c8011dc --- /dev/null +++ b/Yi-1.5-9B-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c377c98a31a36cf7f6aa89169ac486da9036791901aaaf8a574ac76cd70ed3 +size 5328957792 diff --git a/Yi-1.5-9B-Chat-Q4_K_S.gguf b/Yi-1.5-9B-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..352cf76 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b0b20fedc3ea034704a6ec3de78c99037603a04048fa6e468ef3aa685548a5 +size 5071860064 diff --git a/Yi-1.5-9B-Chat-Q5_0.gguf b/Yi-1.5-9B-Chat-Q5_0.gguf new file mode 100644 index 0000000..ffd886f --- /dev/null +++ b/Yi-1.5-9B-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff07070b90245d4fd1aaeb71032c754e7b1e9f84ff438a6f9cb108280150515 +size 6107853152 diff --git a/Yi-1.5-9B-Chat-Q5_K_M.gguf b/Yi-1.5-9B-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..d486e7f --- /dev/null +++ b/Yi-1.5-9B-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7694625433dc9fefc97049ed2041f49410371fae42814ba6bf88edf5d287c0ca +size 6258258272 diff --git a/Yi-1.5-9B-Chat-Q5_K_S.gguf b/Yi-1.5-9B-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..caac2af --- /dev/null +++ b/Yi-1.5-9B-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9505479b63c123cc436d3d513ff29c58401f953a4be05a0bd3ffa82e6babc87a +size 6107853152 diff --git a/Yi-1.5-9B-Chat-Q6_K.gguf b/Yi-1.5-9B-Chat-Q6_K.gguf new file mode 100644 index 0000000..2e587d9 --- /dev/null +++ b/Yi-1.5-9B-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a621864d2f71334a11056539440b30373b8780f3e13e0529ed933ec7cd2c5a +size 7245640032 diff --git a/Yi-1.5-9B-Chat-Q8_0.gguf b/Yi-1.5-9B-Chat-Q8_0.gguf new file mode 100644 index 0000000..e0410cb --- /dev/null +++ b/Yi-1.5-9B-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568d0fb5e52a8bd3ba5bcb92b8908defb6a3f92198729ddf4b811f3c81f3d268 +size 9383915872 diff --git a/Yi-1.5-9B-Chat-f16.gguf b/Yi-1.5-9B-Chat-f16.gguf new file mode 100644 index 0000000..8acae1f --- /dev/null +++ b/Yi-1.5-9B-Chat-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac93eff66e2a4ae3e3da14a29ea4faef65e6f46c78433a5195b1563c7161a6e +size 17661112672 diff --git a/config.json b/config.json new file mode 100644 index 0000000..f41fec6 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0", + "use_cache": false, + "vocab_size": 64000 +} 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