初始化项目，由ModelHub XC社区提供模型

Model: second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF
Source: Original Platform

.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
+NVIDIA-Nemotron-Nano-9B-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+NVIDIA-Nemotron-Nano-9B-v2-f16.gguf filter=lfs diff=lfs merge=lfs -text

NVIDIA-Nemotron-Nano-9B-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f57a12c7ad94e8b1cc14ea907f2bd5388cdf33cc84fa33dcfcd5ef9ff69454
+size 5006192192

NVIDIA-Nemotron-Nano-9B-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b058e30a07a51bc0f17a0438a149c73f36a4599b2138aeab7bfc9a9b1f26911
+size 5488365632

NVIDIA-Nemotron-Nano-9B-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e43dfc95638f6419c9578f17cd06c54486bbdae56e4b988ca7f7cf622d13d28
+size 5379734592

NVIDIA-Nemotron-Nano-9B-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bccd94ad9c0b7db692d3eaad88cfa4525e7f7883c974ba52d1c26918b65e529
+size 5131990592

NVIDIA-Nemotron-Nano-9B-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c515605c77c59e14a5cdaf39143de014439ec9133fc76378c3a89a28e5038d
+size 5308681792

NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651d819385fbb779f0e8a7f620f16526a4a750d8e67b5576b4ca2f8e08f1005f
+size 6525628992

NVIDIA-Nemotron-Nano-9B-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6c681f4c611843a9958bdf72875c16d799141806a07a26d897451fa5b8a653
+size 6211616832

NVIDIA-Nemotron-Nano-9B-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d90a4f7e244eab3310cf7054fb273eb7349eeca0b05841562867605ce8621108
+size 6346034752

NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebd4b15772d96328cf818185cf01ebf295220092e93715df2c58cb4f05e774e
+size 7069805632

NVIDIA-Nemotron-Nano-9B-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261e36ae2fb429c4c54d776a4e3debaae30b6f1716a2e2e2d00a4f92952da404
+size 6781562432

NVIDIA-Nemotron-Nano-9B-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5326e55a77faa3cf99b92528956e479234aae0f6c0e93a4263c4d07b79ab4de
+size 9135892032

NVIDIA-Nemotron-Nano-9B-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a2b34c72e4e1f4da0637381281de0c28d6e886855bab3551bb6c4019be3fb0
+size 9458093632

NVIDIA-Nemotron-Nano-9B-v2-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b9a249328379e31318788a59521e1e86e924819917766d478da217fc4ab126
+size 17788743232

README.md

@@ -0,0 +1,141 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: >-
+  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+base_model: nvidia/NVIDIA-Nemotron-Nano-9B-v2
+model_creator: nvidia
+model_name: NVIDIA-Nemotron-Nano-9B-v2
+quantized_by: Second State Inc.
+pipeline_tag: text-generation
+language:
+- en
+- es
+- fr
+- de
+- it
+- ja
+library_name: transformers
+---
+
+<!-- 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 -->
+
+# NVIDIA-Nemotron-Nano-9B-v2-GGUF
+
+## Original Model
+
+[nvidia/NVIDIA-Nemotron-Nano-9B-v2](https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: coming soon
+
+<!-- - LlamaEdge version: [v0.25.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.25.1) and above -->
+
+- Prompt template
+
+  - Prompt type: `nemotron-2-chat`
+
+  - Prompt string
+    - `Thinking` mode
+
+      ```text
+      <SPECIAL_10>System
+      You are a helpful assistant.
+
+      <SPECIAL_11>User
+      Hi, can you explain what quantum computing is? /think
+
+      <SPECIAL_11>Assistant
+      <think>
+      The user is asking about quantum computing, I should give a simple explanation.
+      </think>
+      Quantum computing uses principles of quantum mechanics, such as superposition and entanglement, to perform computations that would be hard for classical computers.
+      <SPECIAL_12>
+
+      <SPECIAL_11>User
+      That sounds complicated. Can you give me an example? /think
+
+      <SPECIAL_11>Assistant
+      <think>
+      I should give a concrete example, like Shor’s algorithm or Grover’s algorithm, but in simple terms.
+      </think>
+      For example, a quantum computer can factor very large numbers much faster than classical computers, which could break some encryption methods.
+      <SPECIAL_12>
+
+      <SPECIAL_11>User
+      Okay, explain it in a simpler way for a 10-year-old. /think
+
+      <SPECIAL_11>Assistant
+      <think>
+      ```
+
+    - `No-thinking` mode
+
+      ```text
+      <SPECIAL_10>System
+      You are a helpful assistant.
+
+      /no_think
+
+      <SPECIAL_11>User
+      Hi, can you explain what quantum computing is? /no_think
+
+      <SPECIAL_11>Assistant
+      <think></think>
+      Quantum computing is a type of computing that uses the rules of quantum mechanics to solve certain problems faster than regular computers.
+      <SPECIAL_12>
+
+      <SPECIAL_11>User
+      That sounds complicated. Can you give me an example? /no_think
+
+      <SPECIAL_11>Assistant
+      <think></think>
+      For example, quantum computers could quickly factor very large numbers, which is important for cryptography.
+      <SPECIAL_12>
+
+      <SPECIAL_11>User
+      Okay, explain it even more simply. /no_think
+
+      <SPECIAL_11>Assistant
+      <think></think>
+      ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template nemotron-2-chat \
+    --ctx-size 128000 \
+    --model-name nemotron-nano-v2
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q2_K.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q2_K.gguf)     | Q2_K   | 2 | 5.01 GB| smallest, significant quality loss - not recommended for most purposes |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q3_K_L.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q3_K_L.gguf) | Q3_K_L | 3 | 5.49 GB| small, substantial quality loss |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q3_K_M.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q3_K_M.gguf) | Q3_K_M | 3 | 5.38 GB| very small, high quality loss |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q3_K_S.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q3_K_S.gguf) | Q3_K_S | 3 | 5.13 GB| very small, high quality loss |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q4_0.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q4_0.gguf)     | Q4_0   | 4 | 5.31 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q4_K_M.gguf) | Q4_K_M | 4 | 6.53 GB| medium, balanced quality - recommended |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q4_K_S.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q4_K_S.gguf) | Q4_K_S | 4 | 6.21 GB| small, greater quality loss |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q5_0.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q5_0.gguf)     | Q5_0   | 5 | 6.35 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q5_K_M.gguf) | Q5_K_M | 5 | 7.07 GB| large, very low quality loss - recommended |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q5_K_S.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q5_K_S.gguf) | Q5_K_S | 5 | 6.78 GB| large, low quality loss - recommended |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q6_K.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-Q6_K.gguf)     | Q6_K   | 6 | 9.14 GB| very large, extremely low quality loss |
+| [NVIDIA-Nemotron-Nano-9B-v2-Q8_0.gguf](https://huggingface.co/second-state/Nemotron-Mini-4B-Instruct-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-f16.gguf)     | Q8_0   | 8 | 17.8 GB| very large, extremely low quality loss - not recommended |
+| [NVIDIA-Nemotron-Nano-9B-v2-f16.gguf](https://huggingface.co/second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF/blob/main/NVIDIA-Nemotron-Nano-9B-v2-f16-00001-of-00003.gguf)       | f16   | 16 | 30.0 GB|  |
+
+*Quantized with llama.cpp b6315.*

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "NemotronHForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
+    "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
+  },
+  "bos_token_id": 1,
+  "chunk_size": 128,
+  "conv_kernel": 4,
+  "eos_token_id": 12,
+  "head_dim": 128,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4480,
+  "hybrid_override_pattern": "M-M-M-MM-M-M-M*-M-M-M*-M-M-M-M*-M-M-M-M*-M-MM-M-M-M-M-M-",
+  "initializer_range": 0.02,
+  "intermediate_size": 15680,
+  "layer_norm_epsilon": 1e-05,
+  "mamba_head_dim": 80,
+  "mamba_hidden_act": "silu",
+  "mamba_num_groups": 8,
+  "mamba_num_heads": 128,
+  "mamba_proj_bias": false,
+  "mamba_state_dim": 128,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "mlp_hidden_act": "relu2",
+  "model_type": "nemotron_h",
+  "n_groups": 8,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 56,
+  "num_key_value_heads": 8,
+  "num_logits_to_keep": 1,
+  "num_query_groups": 8,
+  "pad_token_id": 0,
+  "rescale_prenorm_residual": true,
+  "residual_in_fp32": false,
+  "rms_norm_eps": 1e-05,
+  "sliding_window": null,
+  "ssm_state_size": 128,
+  "tie_word_embeddings": false,
+  "time_step_floor": 0.0001,
+  "time_step_limit": [
+    0.0,
+    Infinity
+  ],
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 256,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_bias": false,
+  "use_cache": true,
+  "use_conv_bias": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 131072
+}