commit 91dd7b21e0d0998ad0ddcdd028248e1e0cd75973 Author: ModelHub XC Date: Tue May 26 23:32:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: second-state/MistralLite-7B-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/MistralLite-Q2_K.gguf b/MistralLite-Q2_K.gguf new file mode 100644 index 0000000..30e1da0 --- /dev/null +++ b/MistralLite-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f46fbc58f966476d2a906005da7a42d0d2085fc217c5a670487d8a715032d5 +size 2701430240 diff --git a/MistralLite-Q3_K_L.gguf b/MistralLite-Q3_K_L.gguf new file mode 100644 index 0000000..8ee5e6b --- /dev/null +++ b/MistralLite-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02186137e07badb7707e80a8865016c79809d750e2d22bce710ab66b3a4d4329 +size 3822039744 diff --git a/MistralLite-Q3_K_M.gguf b/MistralLite-Q3_K_M.gguf new file mode 100644 index 0000000..9932206 --- /dev/null +++ b/MistralLite-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ead22c59a5c66ef54a875522075dac3686f34214b344bb7586a72b00a36c21c +size 3519001280 diff --git a/MistralLite-Q3_K_S.gguf b/MistralLite-Q3_K_S.gguf new file mode 100644 index 0000000..e6ff92d --- /dev/null +++ b/MistralLite-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df03e3fa1924af92e55b3149c5ba3f586c9901faa063fface1488563413f4165 +size 3164582592 diff --git a/MistralLite-Q4_0.gguf b/MistralLite-Q4_0.gguf new file mode 100644 index 0000000..58454cd --- /dev/null +++ b/MistralLite-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259579cb037ea997b02450e37d676693849429a144ea1b1ce7e40e5ec3f58962 +size 4108933408 diff --git a/MistralLite-Q4_K_M.gguf b/MistralLite-Q4_K_M.gguf new file mode 100644 index 0000000..276373e --- /dev/null +++ b/MistralLite-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0fb6c536e9807fdcd6082c0e760ca582ef93a973e0a6f1e4f9cc19c676ee43 +size 4368455968 diff --git a/MistralLite-Q4_K_S.gguf b/MistralLite-Q4_K_S.gguf new file mode 100644 index 0000000..92fdd0d --- /dev/null +++ b/MistralLite-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eb4e6603a8715deca11969523db2f1e66ee40c1f2d6305db87a3c5c7e014da +size 4140390688 diff --git a/MistralLite-Q5_0.gguf b/MistralLite-Q5_0.gguf new file mode 100644 index 0000000..c89c561 --- /dev/null +++ b/MistralLite-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91397b0810fd6f057807855007ec1a1f6e43c178c285f292f442d4a1d150a585 +size 4997734176 diff --git a/MistralLite-Q5_K_M.gguf b/MistralLite-Q5_K_M.gguf new file mode 100644 index 0000000..69d0219 --- /dev/null +++ b/MistralLite-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f5d6117cc9ec8dceb2e28e1268770c0c32f39949fceceb105d1e0837e07361 +size 5131427616 diff --git a/MistralLite-Q5_K_S.gguf b/MistralLite-Q5_K_S.gguf new file mode 100644 index 0000000..d1aa6af --- /dev/null +++ b/MistralLite-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264516b471a342d9f3c8cbbdcc164645af43463fdd5ceafb034025ce96d452cf +size 4997734176 diff --git a/MistralLite-Q6_K.gguf b/MistralLite-Q6_K.gguf new file mode 100644 index 0000000..726b570 --- /dev/null +++ b/MistralLite-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6cc0771f0f963c56b3b50f7edf011fe30e671ba0834de0c081e5570bbd1f59 +size 5942084992 diff --git a/MistralLite-Q8_0.gguf b/MistralLite-Q8_0.gguf new file mode 100644 index 0000000..3d54778 --- /dev/null +++ b/MistralLite-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321944233d26681cf52905193ba5cc4104d57f3340caf1265c09c4173b54a75f +size 7695883456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..57db2fc --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: amazon/MistralLite +inference: false +license: apache-2.0 +model_creator: Amazon Web Services +model_name: MistralLite 7B +model_type: mistral +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# MistralLite-7B-GGUF + +## Original Model + +[amazon/MistralLite](https://huggingface.co/amazon/MistralLite) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `mistrallite` + + - Prompt string + + ```text + <|prompter|>{user_message}<|assistant|>{assistant_message} + ``` + + - Reverse prompt: `` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-api-server.wasm -p mistrallite -r '' + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:MistralLite-Q5_K_M.gguf llama-chat.wasm -p mistrallite -r '' + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [MistralLite-Q2_K.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q2_K.gguf) | Q2_K | 2 | 2.7 GB| smallest, significant quality loss - not recommended for most purposes | +| [MistralLite-Q3_K_L.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [MistralLite-Q3_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [MistralLite-Q3_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [MistralLite-Q4_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [MistralLite-Q4_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [MistralLite-Q4_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [MistralLite-Q5_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [MistralLite-Q5_K_M.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [MistralLite-Q5_K_S.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended | +| [MistralLite-Q6_K.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [MistralLite-Q8_0.gguf](https://huggingface.co/second-state/MistralLite-7B-GGUF/blob/main/MistralLite-Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..c6d11f6 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "amazon/MistralLite", + "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": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.0", + "use_cache": true, + "vocab_size": 32003 +} 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/mistrallite.Q5_K_M.gguf b/mistrallite.Q5_K_M.gguf new file mode 100644 index 0000000..6b89d6e --- /dev/null +++ b/mistrallite.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d06d149c24eea0446ea7aad596aca396fe7f3302441e9375d5bbd3fd9ba8ebea +size 5131427680