commit 7a0fef26af85b80e68ab57dc90c034b46c35c292
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Apr 18 12:29:01 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: RedHatAI/Nous-Hermes-2-SOLAR-10.7B-pruned2.4
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..a6344aa
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..f2cda0c
--- /dev/null
+++ b/README.md
@@ -0,0 +1,86 @@
+---
+base_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
+inference: True
+model_type: Llama
+tags:
+- nm-vllm
+- sparse
+---
+## Nous-Hermes-2-SOLAR-10.7B-pruned2.4
+This repo contains model files for [Nous-Hermes-2-SOLAR-10.7B](https://huggingface.co/NousResearch/Nous-Hermes-2-SOLAR-10.7B) optimized for [NM-vLLM](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
+
+This model was pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [SparseML](https://github.com/neuralmagic/sparseml).
+
+## Inference
+Install [NM-vLLM](https://github.com/neuralmagic/nm-vllm) for fast inference and low memory-usage: 
+```bash
+pip install nm-vllm[sparse]
+```
+Run in a Python pipeline for local inference:
+```python
+from vllm import LLM, SamplingParams
+
+model = LLM("nm-testing/Nous-Hermes-2-SOLAR-10.7B-pruned2.4", sparsity="semi_structured_sparse_w16a16")
+prompt = "How to make banana bread?"
+formatted_prompt =  f"<|im_start|>User:{prompt}\n<|im_start|>assistant:\n"
+
+sampling_params = SamplingParams(max_tokens=100)
+outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+"""
+To make banana bread, you will need to follow these steps:
+
+1. Gather the ingredients needed for the recipe: flour, sugar, eggs, baking powder, and banana bread.
+2. Preparing the bread by kneading the flour, butter, and sugar in a bowl until it becomes soft.
+3. Then, knead the bread with the flour eggs and sugar then bake them in a microwave oven.
+4. Once done baking a
+"""
+```
+
+## Prompt template
+
+```
+### User:
+{prompt}
+### Assistant:"
+```
+
+## Sparsification
+For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.
+
+Install [SparseML](https://github.com/neuralmagic/sparseml):
+```bash
+git clone https://github.com/neuralmagic/sparseml
+pip install -e "sparseml[transformers]"
+```
+
+Replace the recipe as you like and run this one-shot compression script to apply SparseGPT:
+```python
+import sparseml.transformers
+
+original_model_name = "NousResearch/Nous-Hermes-2-SOLAR-10.7B"
+calibration_dataset = "open_platypus"
+output_directory = "output/"
+
+recipe = """
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      sequential_update: true
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']
+"""
+
+# Apply SparseGPT to the model
+sparseml.transformers.oneshot(
+    model=original_model_name,
+    dataset=calibration_dataset,
+    recipe=recipe,
+    output_dir=output_directory,
+)
+```
+
+## Slack
+
+For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)
\ No newline at end of file
diff --git a/added_tokens.json b/added_tokens.json
new file mode 100644
index 0000000..e36863d
--- /dev/null
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..e3a9092
--- /dev/null
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "NousResearch/Nous-Hermes-2-SOLAR-10.7B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "1.7.0.20240130",
+  "use_cache": false,
+  "vocab_size": 32002
+}
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/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..0487227
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "1.7.0.20240130",
+  "use_cache": false
+}
diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin
new file mode 100644
index 0000000..94454b5
--- /dev/null
+++ b/pytorch_model-00001-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed2cb596fad74ccb18aa636354690bdd2992d478e7bf068d059ab5b238ebd11
+size 9943047731
diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin
new file mode 100644
index 0000000..67b4b87
--- /dev/null
+++ b/pytorch_model-00002-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d76fd6feb9ce88e12f8031e01503a3570c61a37472aee40b572c9816ebf0f40
+size 9999672004
diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin
new file mode 100644
index 0000000..4bf9c56
--- /dev/null
+++ b/pytorch_model-00003-of-00003.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071f3f746b784749b751dd5f17363f481fad153e7ff12f58316d0307564c3167
+size 1520518398
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..028b326
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a69d65b1746107fddf021a005d3f361aa41519fba491ce9dc6f1325bceeb63b
+size 35838
diff --git a/recipe.yaml b/recipe.yaml
new file mode 100644
index 0000000..0ebaee5
--- /dev/null
+++ b/recipe.yaml
@@ -0,0 +1,10 @@
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      block_size: 128
+      sequential_update: true
+      quantize: false
+      percdamp: 0.01
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..d555d77
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..bc4ac00
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af1053883a8321feeb320cf42c61eb4ced06511f6a2546d9a879e0c0def91e6
+size 1795678
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..8b443ef
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..1d085de
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052d53db68a57524167aadb25ffeca49f19eed37fbe3e18e24aba94f53a3b762
+size 1601