commit d85f37be95bb1cf00c0d84b974a117cf4fd035a6 Author: ModelHub XC Date: Wed May 27 00:48:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Mistral-7B-Instruct-v0.2-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-v0.2-Q2_K.gguf b/Mistral-7B-Instruct-v0.2-Q2_K.gguf new file mode 100644 index 0000000..1e533ac --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061863aa59c706501c703c785276034a66703f50803b007a533b3df8bdecd9a0 +size 3083098304 diff --git a/Mistral-7B-Instruct-v0.2-Q3_K_L.gguf b/Mistral-7B-Instruct-v0.2-Q3_K_L.gguf new file mode 100644 index 0000000..065be03 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11cd57a796963d408ed8951b934130def4cab5819962f44c36a76e3c7c1c1a5 +size 3822024896 diff --git a/Mistral-7B-Instruct-v0.2-Q3_K_M.gguf b/Mistral-7B-Instruct-v0.2-Q3_K_M.gguf new file mode 100644 index 0000000..b4cb0d8 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bcf73c2c8b9b1f018e6f278980549b75f8993f0f8f6e3275571fdd3013da51 +size 3518986432 diff --git a/Mistral-7B-Instruct-v0.2-Q3_K_S.gguf b/Mistral-7B-Instruct-v0.2-Q3_K_S.gguf new file mode 100644 index 0000000..d31ad64 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c57d1204f7e22efcb7f6ea7c4e5ef81b99b1234286d05c1d3804dca80516266 +size 3164567744 diff --git a/Mistral-7B-Instruct-v0.2-Q4_0.gguf b/Mistral-7B-Instruct-v0.2-Q4_0.gguf new file mode 100644 index 0000000..de0837a --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:141da842f1cd9dd6be6cdd0d79cfc1b04a660805f9608c1475e16ce5beb138f2 +size 4108916928 diff --git a/Mistral-7B-Instruct-v0.2-Q4_K_M.gguf b/Mistral-7B-Instruct-v0.2-Q4_K_M.gguf new file mode 100644 index 0000000..6a80dc6 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14268497e591764a76c9f8085448ca97722f27e85bb89c795d292545e1200a97 +size 4368439488 diff --git a/Mistral-7B-Instruct-v0.2-Q4_K_S.gguf b/Mistral-7B-Instruct-v0.2-Q4_K_S.gguf new file mode 100644 index 0000000..efbb736 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b5b4fae8e2461e03411f98f9c7b8fc23cfdf88b63a1222c5021edb338411b9 +size 4140374208 diff --git a/Mistral-7B-Instruct-v0.2-Q5_0.gguf b/Mistral-7B-Instruct-v0.2-Q5_0.gguf new file mode 100644 index 0000000..2d61ddf --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562b5f2928928dbd3a65cc5a32190127b62a0fc1a15abd48fc199f679bb4730f +size 4997716160 diff --git a/Mistral-7B-Instruct-v0.2-Q5_K_M.gguf b/Mistral-7B-Instruct-v0.2-Q5_K_M.gguf new file mode 100644 index 0000000..0b8c68e --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce9a46d73b47ca1d46aa0f182c12bd18ee2f3bcfffcc397de191ae31c3c3c4e +size 5131409600 diff --git a/Mistral-7B-Instruct-v0.2-Q5_K_S.gguf b/Mistral-7B-Instruct-v0.2-Q5_K_S.gguf new file mode 100644 index 0000000..e611385 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a917883b9af98183513cb526477096894b548f820aaf5834790b4ec52082b36a +size 4997716160 diff --git a/Mistral-7B-Instruct-v0.2-Q6_K.gguf b/Mistral-7B-Instruct-v0.2-Q6_K.gguf new file mode 100644 index 0000000..b91020f --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eae3811bfd827819082fa1c011644dd108e5519f6d1da07ad1db23b6e9d2bac +size 5942065344 diff --git a/Mistral-7B-Instruct-v0.2-Q8_0.gguf b/Mistral-7B-Instruct-v0.2-Q8_0.gguf new file mode 100644 index 0000000..cc2ecf7 --- /dev/null +++ b/Mistral-7B-Instruct-v0.2-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1909b6abaef7c10378f7795396356ab308a8bd8809373b0016a8334287559e07 +size 7695857856 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dcf2013 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: mistralai/Mistral-7B-Instruct-v0.2 +inference: false +library_name: transformers +license: apache-2.0 +model_creator: mistralai +model_name: Mistral 7B Instruct v0.2 +model_type: mistral +pipeline_tag: text-generation +tags: +- finetuned +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Mistral-7B-Instruct-v0.2-GGUF + +## Original Model + +[mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) + +## 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-v0.2-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-v0.2-Q5_K_M.gguf llama-chat.wasm -p mistral-instruct + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Mistral-7B-Instruct-v0.2-Q2_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q2_K.gguf) | Q2_K | 2 | 3.08 GB| smallest, significant quality loss - not recommended for most purposes | +| [Mistral-7B-Instruct-v0.2-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [Mistral-7B-Instruct-v0.2-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.2-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.2-Q4_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Mistral-7B-Instruct-v0.2-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [Mistral-7B-Instruct-v0.2-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [Mistral-7B-Instruct-v0.2-Q5_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q5_0.gguf) | Q5_0 | 5 | 5 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Mistral-7B-Instruct-v0.2-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [Mistral-7B-Instruct-v0.2-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q5_K_S.gguf) | Q5_K_S | 5 | 5 GB| large, low quality loss - recommended | +| [Mistral-7B-Instruct-v0.2-Q6_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [Mistral-7B-Instruct-v0.2-Q8_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.2-GGUF/blob/main/Mistral-7B-Instruct-v0.2-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..c0519dc --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "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": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.0", + "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