初始化项目，由ModelHub XC社区提供模型

Model: second-state/Mistral-Nemo-Instruct-2407-GGUF Source: Original Platform
2026-07-05 04:16:12 +08:00
commit 717a3f948f
17 changed files with 201 additions and 0 deletions
--- a/.gitattributes
+++ 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-Nemo-Instruct-2407-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-Nemo-Instruct-2407-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Mistral-Nemo-Instruct-2407-Q2_K.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea290d014fa76c3cf7e0a3021094ede6d8cf8195becfd55e726bf2fed9a735b
+size 4791047872
--- a/Mistral-Nemo-Instruct-2407-Q3_K_L.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27eb59d2642133da264bb15f9f998a361228790e6cb72abefa533c22841e1b65
+size 6561502912
--- a/Mistral-Nemo-Instruct-2407-Q3_K_M.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634e7fac8c9e6830295331ae54182c000a1cef492d26a0f57138f4a7bf28b2de
+size 6083090112
--- a/Mistral-Nemo-Instruct-2407-Q3_K_S.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3842eb732ce303a2ad5989c897825d9c2b0df50bbda29a80b4412043c76663b
+size 5534226112
--- a/Mistral-Nemo-Instruct-2407-Q4_0.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7817bc6f4b3891d2aa6003bd8a826554cab4acec14d46c91e898e31251af7f3f
+size 7071700672
--- a/Mistral-Nemo-Instruct-2407-Q4_K_M.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:186ac886e5cf42a6ca0815e60504f13c7cc95446eb05ac2f1515e388976cebcf
+size 7477204672
--- a/Mistral-Nemo-Instruct-2407-Q4_K_S.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00eda01cc0a4868050e4bd64fdf4890d940d7c756a29901225c8ffd61d1b4ac8
+size 7120197312
--- a/Mistral-Nemo-Instruct-2407-Q5_0.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66aec032377d2c767a13f89c0149023f5283635de9a4389bd54e16ed3f99051
+size 8518735552
--- a/Mistral-Nemo-Instruct-2407-Q5_K_M.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdc6d65155e7908af3b9675a84f08400d0df8bc470281ec5d183f5d886a4824a
+size 8727631552
--- a/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ce16c9a4ec48d02cdbe4bdef829e7f628ebae05bddad6ba1aab7c0cf37d782
+size 8518735552
--- a/Mistral-Nemo-Instruct-2407-Q6_K.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48318ea51217b0c92a12314d738a5982b273c5d335c118a903c0b3a96756977a
+size 10056210112
--- a/Mistral-Nemo-Instruct-2407-Q8_0.gguf
+++ b/Mistral-Nemo-Instruct-2407-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824229be17606dd8177fc91c1d330b065bc4f3de2873eab614376b988dcbf48a
+size 13022369472
--- a/Mistral-Nemo-Instruct-2407-f16.gguf
+++ b/Mistral-Nemo-Instruct-2407-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a9581ae7a87e5727aa1b0670f439ffe2a31a4bcb38ca201f9cd76ac975d31ae
+size 24504276672
--- a/README.md
+++ b/README.md
@@ -0,0 +1,87 @@
+---
+license: apache-2.0
+model_name: Mistral-Nemo-Instruct-2407
+base_model: mistralai/Mistral-Nemo-Instruct-2407
+inference: false
+model_creator: mistralai
+quantized_by: Second State Inc.
+language:
+  - en
+  - fr
+  - de
+  - es
+  - it
+  - pt
+  - ru
+  - zh
+  - ja
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Mistral-Nemo-Instruct-2407-GGUF
+
+## Original Model
+
+[mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4)
+
+- Prompt template
+
+  - Prompt type: `mistral-instruct`
+
+  - Prompt string
+
+    ```text
+    <s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template mistral-instruct \
+    --ctx-size 128000 \
+    --model-name Mistral-Nemo-Instruct-2407
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Nemo-Instruct-2407-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template mistral-instruct \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Mistral-Nemo-Instruct-2407-Q2_K.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q2_K.gguf)         | Q2_K   | 2 | 4.79 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Mistral-Nemo-Instruct-2407-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_L.gguf)     | Q3_K_L | 3 | 6.56 GB| small, substantial quality loss |
+| [Mistral-Nemo-Instruct-2407-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_M.gguf)     | Q3_K_M | 3 | 6.08 GB| very small, high quality loss |
+| [Mistral-Nemo-Instruct-2407-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_S.gguf)     | Q3_K_S | 3 | 5.53 GB| very small, high quality loss |
+| [Mistral-Nemo-Instruct-2407-Q4_0.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0.gguf)         | Q4_0   | 4 | 7.07 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Mistral-Nemo-Instruct-2407-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_M.gguf)     | Q4_K_M | 4 | 7.48 GB| medium, balanced quality - recommended |
+| [Mistral-Nemo-Instruct-2407-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_S.gguf)     | Q4_K_S | 4 | 7.12 GB| small, greater quality loss |
+| [Mistral-Nemo-Instruct-2407-Q5_0.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_0.gguf)         | Q5_0   | 5 | 8.52 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Mistral-Nemo-Instruct-2407-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/resolve/main/Mistral-Nemo-Instruct-2407-Q5_K_M.gguf)  | Q5_K_M | 5 | 8.73 GB| large, very low quality loss - recommended |
+| [Mistral-Nemo-Instruct-2407-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q5_K_S.gguf)     | Q5_K_S | 5 | 8.52 GB| large, low quality loss - recommended |
+| [Mistral-Nemo-Instruct-2407-Q6_K.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K.gguf)         | Q6_K   | 6 | 10.1 GB| very large, extremely low quality loss |
+| [Mistral-Nemo-Instruct-2407-Q8_0.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q8_0.gguf)         | Q8_0   | 8 | 13.0 GB| very large, extremely low quality loss - not recommended |
+| [Mistral-Nemo-Instruct-2407-f16.gguf](https://huggingface.co/second-state/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f16.gguf)           | f16   | 16 | 24.5 GB|  |
+
+*Quantized with llama.cpp b3438.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "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": "4.43.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`