commit 2796369f0b00ebdcacb9297614ba8f426e3b6a6f Author: ModelHub XC Date: Tue Sep 8 18:10:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Mistral-7B-Instruct-v0.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b26a8cb --- /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 +Mistral-7B-Instruct-v0.3-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Instruct-v0.3-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Instruct-v0.3-Q2_K.gguf b/Mistral-7B-Instruct-v0.3-Q2_K.gguf new file mode 100644 index 0000000..6caa9a6 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bc6b15314eef91fa160a03a4d9879c281c8249c02a2bb2f3493e3cd1027238 +size 2722877440 diff --git a/Mistral-7B-Instruct-v0.3-Q3_K_L.gguf b/Mistral-7B-Instruct-v0.3-Q3_K_L.gguf new file mode 100644 index 0000000..ebb656b --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:116cc14628e1fc29f770d10ba6518d17437e35512662dcb72a820c03c21bf70a +size 3825979392 diff --git a/Mistral-7B-Instruct-v0.3-Q3_K_M.gguf b/Mistral-7B-Instruct-v0.3-Q3_K_M.gguf new file mode 100644 index 0000000..9fe4794 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca4407b2bd6728710a472f117e9fd4fa35b22d304d24bdc48afdb26bacf55b2 +size 3522940928 diff --git a/Mistral-7B-Instruct-v0.3-Q3_K_S.gguf b/Mistral-7B-Instruct-v0.3-Q3_K_S.gguf new file mode 100644 index 0000000..a6176f7 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57a457e3cddb31b5ad9a09bbedbe7ec7cb6e4ae646f24b893372ddcffe3d998 +size 3168522240 diff --git a/Mistral-7B-Instruct-v0.3-Q4_0.gguf b/Mistral-7B-Instruct-v0.3-Q4_0.gguf new file mode 100644 index 0000000..3942212 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897f787720be439f931962a100b4f107af4966342654086a1c975e30c31c0e32 +size 4113289216 diff --git a/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf b/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf new file mode 100644 index 0000000..92f015d --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55bc8ab878fb93cb61660278a731373e056f40b2cc4056f1f43941f0cbd8444 +size 4372811776 diff --git a/Mistral-7B-Instruct-v0.3-Q4_K_S.gguf b/Mistral-7B-Instruct-v0.3-Q4_K_S.gguf new file mode 100644 index 0000000..71105c5 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d1368abb224d2ffcffc1f616b10d95041f6f35e51af468ccc7752b7af2629fe +size 4144746496 diff --git a/Mistral-7B-Instruct-v0.3-Q5_0.gguf b/Mistral-7B-Instruct-v0.3-Q5_0.gguf new file mode 100644 index 0000000..57912b4 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c803428861b2e4e5956d5b6019b45207c9000c30518b2233a15da19b3345d8c3 +size 5002481664 diff --git a/Mistral-7B-Instruct-v0.3-Q5_K_M.gguf b/Mistral-7B-Instruct-v0.3-Q5_K_M.gguf new file mode 100644 index 0000000..b0cd5f4 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8b4eb274aaa64442507b62d49b5133a21053c32801d2bcce149eb78ed26971 +size 5136175104 diff --git a/Mistral-7B-Instruct-v0.3-Q5_K_S.gguf b/Mistral-7B-Instruct-v0.3-Q5_K_S.gguf new file mode 100644 index 0000000..c7f0bc7 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6972c8f0c980f5e97888d500370e0740d076d435c7145e08b9111b8195e76484 +size 5002481664 diff --git a/Mistral-7B-Instruct-v0.3-Q6_K.gguf b/Mistral-7B-Instruct-v0.3-Q6_K.gguf new file mode 100644 index 0000000..7902f04 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7d028c0db4b6b0cc780c4173752021b413d486707970c5d1fc270671a2addf1 +size 5947248640 diff --git a/Mistral-7B-Instruct-v0.3-Q8_0.gguf b/Mistral-7B-Instruct-v0.3-Q8_0.gguf new file mode 100644 index 0000000..6fe9af3 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3776268f275f5d448bfb6d14288ed858bde5502e63fc52b1f24fb30884b0d9a0 +size 7702564864 diff --git a/Mistral-7B-Instruct-v0.3-f16.gguf b/Mistral-7B-Instruct-v0.3-f16.gguf new file mode 100644 index 0000000..2862a27 --- /dev/null +++ b/Mistral-7B-Instruct-v0.3-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd9070b42b8788becde8959d2924489cc1226e3104272f93ae8403e98e9be30 +size 14497337344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a54ae42 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +license: apache-2.0 +model_name: Mistral-7B-Instruct-v0.3 +base_model: mistralai/Mistral-7B-Instruct-v0.3 +inference: false +model_creator: mistralai +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Mistral-7B-Instruct-v0.3-GGUF + +## Original Model + +[mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) +## Run with LlamaEdge + +- LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2) + +- Prompt template + + - Prompt type: `mistral-instruct` + + - Prompt string + + ```text + [INST] {user_message_1} [/INST]{assistant_message_1}[INST] {user_message_2} [/INST]{assistant_message_2} + ``` + +- Context size: `32000` + +- Run as LlamaEdge service + + - Chat + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-7B-Instruct-v0.3-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template mistral-instruct \ + --ctx-size 32000 \ + --model-name Mistral-7B-Instruct-v0.3 + ``` + + - Tool use + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-7B-Instruct-v0.3-Q5_K_M.gguf \ + llama-api-server.wasm \ + --prompt-template mistral-tool \ + --ctx-size 32000 \ + --model-name Mistral-7B-Instruct-v0.3 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-7B-Instruct-v0.3-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template mistral-instruct \ + --ctx-size 32000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Mistral-7B-Instruct-v0.3-Q2_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q2_K.gguf) | Q2_K | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes | +| [Mistral-7B-Instruct-v0.3-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q3_K_L.gguf) | Q3_K_L | 3 | 3.83 GB| small, substantial quality loss | +| [Mistral-7B-Instruct-v0.3-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.3-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q3_K_S.gguf) | Q3_K_S | 3 | 3.17 GB| very small, high quality loss | +| [Mistral-7B-Instruct-v0.3-Q4_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Mistral-7B-Instruct-v0.3-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [Mistral-7B-Instruct-v0.3-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [Mistral-7B-Instruct-v0.3-Q5_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q5_0.gguf) | Q5_0 | 5 | 5 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Mistral-7B-Instruct-v0.3-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q5_K_M.gguf) | Q5_K_M | 5 | 5.14 GB| large, very low quality loss - recommended | +| [Mistral-7B-Instruct-v0.3-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q5_K_S.gguf) | Q5_K_S | 5 | 5 GB| large, low quality loss - recommended | +| [Mistral-7B-Instruct-v0.3-Q6_K.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q6_K.gguf) | Q6_K | 6 | 5.95 GB| very large, extremely low quality loss | +| [Mistral-7B-Instruct-v0.3-Q8_0.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-Q8_0.gguf) | Q8_0 | 8 | 7.7 GB| very large, extremely low quality loss - not recommended | +| [Mistral-7B-Instruct-v0.3-f16.gguf](https://huggingface.co/second-state/Mistral-7B-Instruct-v0.3-GGUF/blob/main/Mistral-7B-Instruct-v0.3-f16.gguf) | f16 | 16 | 14.5 GB| | + +*Quantized with llama.cpp b3030.* diff --git a/config.json b/config.json new file mode 100644 index 0000000..7fdb4e3 --- /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": "4.42.0.dev0", + "use_cache": true, + "vocab_size": 32768 +} \ No newline at end of file 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