commit 37ad58fe133770bdff7616a408db2d8c3560d69a Author: ModelHub XC Date: Fri May 29 13:10:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Mistral-7B-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.1-Q2_K.gguf b/Mistral-7B-Instruct-v0.1-Q2_K.gguf new file mode 100644 index 0000000..ab76d7d --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558da6444cf2113c71ab03b75f5bebe261f5bf5ecefa9118df1eef2bf84cfbd9 +size 2701416672 diff --git a/Mistral-7B-Instruct-v0.1-Q3_K_L.gguf b/Mistral-7B-Instruct-v0.1-Q3_K_L.gguf new file mode 100644 index 0000000..d834b48 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be10c4426a7366a3ecd92dea0e30d2e1650aac8773976550ffc7fbaba3a2721 +size 3822024928 diff --git a/Mistral-7B-Instruct-v0.1-Q3_K_M.gguf b/Mistral-7B-Instruct-v0.1-Q3_K_M.gguf new file mode 100644 index 0000000..be271bd --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1234750a52edd6f461f3d16030c4cd48d8766d73e05737f0e3a0ada8feee62a6 +size 3518986464 diff --git a/Mistral-7B-Instruct-v0.1-Q3_K_S.gguf b/Mistral-7B-Instruct-v0.1-Q3_K_S.gguf new file mode 100644 index 0000000..1de0d35 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa28f5fffbb98372f06b34e56ef39b5d1c115d1b927d3c4beda0ba5740f6f40 +size 3164567776 diff --git a/Mistral-7B-Instruct-v0.1-Q4_0.gguf b/Mistral-7B-Instruct-v0.1-Q4_0.gguf new file mode 100644 index 0000000..ed2d365 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d0252b30aa4b4dbbb0c596e07c60c4a83b7068071a6c7c3c2163f1c46e9a61 +size 4108916960 diff --git a/Mistral-7B-Instruct-v0.1-Q4_K_M.gguf b/Mistral-7B-Instruct-v0.1-Q4_K_M.gguf new file mode 100644 index 0000000..2dd2c6f --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3952bb238caf9137ae87a6a0b5591211f25b7753c9ad55267b92c4ae2ea27682 +size 4368439520 diff --git a/Mistral-7B-Instruct-v0.1-Q4_K_S.gguf b/Mistral-7B-Instruct-v0.1-Q4_K_S.gguf new file mode 100644 index 0000000..8cd0c29 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db6cb5c7d4f4f0639fa43bb327ce001fe4696bd5e9327c0f7dcdfdf1e86a0a9 +size 4140374240 diff --git a/Mistral-7B-Instruct-v0.1-Q5_0.gguf b/Mistral-7B-Instruct-v0.1-Q5_0.gguf new file mode 100644 index 0000000..206b614 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0afee75ec1573c222bb36280c99754fb564063a490a3bd3162cd009c3410ad59 +size 4997716192 diff --git a/Mistral-7B-Instruct-v0.1-Q5_K_M.gguf b/Mistral-7B-Instruct-v0.1-Q5_K_M.gguf new file mode 100644 index 0000000..58b4197 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287a6520a937fcdb9d1d21b1f9145ba3c8624a4c8ce5411dae5e74991a911a94 +size 5131409632 diff --git a/Mistral-7B-Instruct-v0.1-Q5_K_S.gguf b/Mistral-7B-Instruct-v0.1-Q5_K_S.gguf new file mode 100644 index 0000000..dd129f3 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe65581a8e41635b1c651856d6cbcb54d9ca434b61245ec2c6670478a793484 +size 4997716192 diff --git a/Mistral-7B-Instruct-v0.1-Q6_K.gguf b/Mistral-7B-Instruct-v0.1-Q6_K.gguf new file mode 100644 index 0000000..8c19c78 --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c7c6584a89cc8deee9f70ffa13429665b19f49fa5efff4269b6ba158162124 +size 5942065376 diff --git a/Mistral-7B-Instruct-v0.1-Q8_0.gguf b/Mistral-7B-Instruct-v0.1-Q8_0.gguf new file mode 100644 index 0000000..eeb064f --- /dev/null +++ b/Mistral-7B-Instruct-v0.1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e87deac3a32c3b0a127da5dde0540364888be0d0892303d0e600a10b8ab2ad3 +size 7695857888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec8895e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mistralai/Mistral-7B-Instruct-v0.1 +inference: false +license: apache-2.0 +model_creator: Mistral AI +model_name: Mistral 7B Instruct v0.1 +model_type: mistral +pipeline_tag: text-generation +tags: +- finetuned +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Mistral-7B-Instruct-v0.1-GGUF + +## Original Model + +[mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `mistral-instruct` + + - Prompt string + + ```text + [INST] {prompt} [/INST] + ``` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-7B-Instruct-v0.1-Q5_K_M.gguf llama-api-server.wasm -p mistral-instruct + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-7B-Instruct-v0.1-Q5_K_M.gguf llama-chat.wasm -p mistral-instruct + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Mistral-7B-Instruct-v0.1-Q2_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q2_K.gguf) | Q2_K | 2 | 2.7 GB| smallest, significant quality loss - not recommended for most purposes | +| [Mistral-7B-Instruct-v0.1-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [Mistral-7B-Instruct-v0.1-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.1-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.1-Q4_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Mistral-7B-Instruct-v0.1-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [Mistral-7B-Instruct-v0.1-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [Mistral-7B-Instruct-v0.1-Q5_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q5_0.gguf) | Q5_0 | 5 | 5 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Mistral-7B-Instruct-v0.1-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [Mistral-7B-Instruct-v0.1-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q5_K_S.gguf) | Q5_K_S | 5 | 5 GB| large, low quality loss - recommended | +| [Mistral-7B-Instruct-v0.1-Q6_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [Mistral-7B-Instruct-v0.1-Q8_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.1-GGUF/blob/main/Mistral-7B-Instruct-v0.1-Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..f4989f0 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} 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 diff --git a/mistral-7b-instruct-v0.1.Q4_K_M.gguf b/mistral-7b-instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..03e7dea --- /dev/null +++ b/mistral-7b-instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14466f9d658bf4a79f96c3f3f22759707c291cac4e62fea625e80c7d32169991 +size 4368438944 diff --git a/mistral-7b-instruct-v0.1.Q5_K_M.gguf b/mistral-7b-instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..520c2d8 --- /dev/null +++ b/mistral-7b-instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b062ec7f0f160e848a0e34c4e291b9e39b3fc60df5b201c038e7064dbbdcdc +size 5131409056