初始化项目，由ModelHub XC社区提供模型

Model: RedHatAI/TinyLlama-1.1B-Chat-v1.0-pruned2.4
Source: Original Platform

.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

README.md

@@ -0,0 +1,96 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+inference: true
+model_type: Llama
+hardware_tag:
+- Intel Xeon
+license: apache-2.0
+license_name: apache-2.0
+license_link: >-
+  https://choosealicense.com/licenses/apache-2.0/
+name: RedHatAI/TinyLlama-1.1B-Chat-v1.0-pruned2.4
+description: >-
+  Pruned TinyLlama model. 
+readme: >-
+  https://huggingface.co/RedHatAI/TinyLlama-1.1B-Chat-v1.0-pruned2.4/blob/main/README.md
+tags:
+- nm-vllm
+- sparse
+---
+## TinyLlama-1.1B-Chat-v1.0-pruned2.4
+This repo contains model files for [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) 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/TinyLlama-1.1B-Chat-v1.0-pruned2.4", sparsity="semi_structured_sparse_w16a16")
+prompt = "How to make banana bread?"
+formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+
+sampling_params = SamplingParams(max_tokens=100,temperature=0,repetition_penalty=1.3)
+outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
+"""
+Banana bread is a delicious dessert that is made with bananas. Here is how to make banana bread:
+
+1. Firstly, you need to cut bananas into small pieces.
+2. Then, you need to slice the bananas into small pieces
+"""
+```
+
+## Prompt template
+
+```
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>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 = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+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)

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "1.7.0.20240130",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "1.7.0.20240130"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:713193f5316dfd143409c67532d10d8674100aa1082229273ddb2574525306e4
+size 2200164718

recipe.yaml

@@ -0,0 +1,10 @@
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      block_size: 128
+      sequential_update: false
+      quantize: false
+      percdamp: 0.01
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b16520bbfede7dc208605369b0e6e08bfdaecbbc0f9ec709eccecbcef37f5b3
+size 1843031

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b41ba7d0eb91e77914ca3dafde559ea3e19878769b7e68409e89bed5222e77a
+size 1289