初始化项目，由ModelHub XC社区提供模型

Model: RedHatAI/Llama-2-7b-ultrachat200k-pruned_70
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 +1,70 @@
+---
+base_model: neuralmagic/Llama-2-7b-pruned70-retrained
+inference: true
+model_type: llama
+pipeline_tag: text-generation
+datasets:
+  - cerebras/SlimPajama-627B
+  - HuggingFaceH4/ultrachat_200k
+tags:
+- sparse
+- chat
+---
+
+# Llama-2-7b-pruned70-retrained-ultrachat
+
+This repo contains a [70% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) finetuned for chat tasks using the [UltraChat 200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.
+
+Official model weights from [Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment](https://arxiv.org/abs/2405.03594).
+
+**Authors**: Neural Magic, Cerebras
+
+## Usage
+
+Below we share some code snippets on how to get quickly started with running the model.
+
+### Sparse Transfer
+
+By leveraging a pre-sparsified model's structure, you can efficiently fine-tune on new data, leading to reduced hyperparameter tuning, training times, and computational costs. Learn about this process [here](https://neuralmagic.github.io/docs-v2/get-started/transfer).
+
+### Running the model
+
+This model may be run with the transformers library. For accelerated inference with sparsity, deploy with [nm-vllm](https://github.com/neuralmagic/nm-vllm) or [deepsparse](https://github.com/neuralmagic/deepsparse).
+
+```python
+# pip install transformers accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained-ultrachat")
+model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained-ultrachat", device_map="auto")
+
+input_text = "Write me a poem about Machine Learning."
+input_ids = tokenizer.apply_chat_template(input_text, add_generation_prompt=True, return_tensors="pt").to("cuda")
+
+outputs = model.generate(**input_ids)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Evaluation Benchmark Results
+
+Model evaluation metrics and results.
+
+| Benchmark                                      | Metric        | Llama-2-7b-ultrachat  | Llama-2-7b-pruned70-retrained-ultrachat |
+|------------------------------------------------|---------------|-------------|-------------------------------|
+| [MMLU](https://arxiv.org/abs/2009.03300)       | 5-shot        | 46.1%       | 32.5%                         |
+| [HellaSwag](https://arxiv.org/abs/1905.07830)  | 0-shot        | 75.9%       | 68.9%                         |
+| [WinoGrande](https://arxiv.org/abs/1907.10641) | 5-shot        | 72.6%       | 65.1%                         |
+| [ARC-c](https://arxiv.org/abs/1911.01547)      | 25-shot       | 52.8%       | 45.3%                         |
+| [TruthfulQA](https://arxiv.org/abs/2109.07958) | 5-shot        | 44.8%       | 39.6%                         |
+| [GSM8K](https://arxiv.org/abs/2110.14168)      | 5-shot        | 12.4%       | 4.8%                          |
+| [AlpacaEval](https://arxiv.org/abs/2107.03374) ([Llama-2-70b-chat-hf](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) evaluator) | Win rate  | 57.6% | 57.4% |
+| [AlpacaEval](https://arxiv.org/abs/2107.03374) (GPT-4 Turbo evaluator) | Win rate  | 60.6% | 54.0% |
+
+## Model Training Details
+
+This model was obtained by sparse-tranfer of the sparse foundational model [Llama-2-7b-pruned70-retrained](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) on the [ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.
+Training was performed for 2 epochs and used the [SquareHead](https://arxiv.org/abs/2310.06927) knowledge distillation with [Llama-2-7b-ultrachat](https://huggingface.co/neuralmagic/Llama-2-7b-ultrachat) as teacher.
+
+## Help
+
+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)

arc_challenge_25shot_bs16_bf16.json

@@ -0,0 +1,25 @@
+{
+  "results": {
+    "arc_challenge": {
+      "acc": 0.4232081911262799,
+      "acc_stderr": 0.014438036220848027,
+      "acc_norm": 0.45307167235494883,
+      "acc_norm_stderr": 0.01454689205200563
+    }
+  },
+  "versions": {
+    "arc_challenge": 0
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
+    "num_fewshot": 25,
+    "batch_size": "16",
+    "batch_sizes": [],
+    "device": "cuda:1",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "neuralmagic/Llama-2-7b-pruned70-retrained-ultrachat",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0"
+}

gsm8k_5shot_bs16_bf16.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "gsm8k": {
+      "acc": 0.047763457164518575,
+      "acc_stderr": 0.005874387536229333
+    }
+  },
+  "versions": {
+    "gsm8k": 0
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
+    "num_fewshot": 5,
+    "batch_size": "16",
+    "batch_sizes": [],
+    "device": "cuda:6",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

hellaswag_10shot_bs16_bf16.json

@@ -0,0 +1,25 @@
+{
+  "results": {
+    "hellaswag": {
+      "acc": 0.5220075682135032,
+      "acc_stderr": 0.004984945635998312,
+      "acc_norm": 0.6885082652857997,
+      "acc_norm_stderr": 0.004621568125102052
+    }
+  },
+  "versions": {
+    "hellaswag": 0
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
+    "num_fewshot": 10,
+    "batch_size": "16",
+    "batch_sizes": [],
+    "device": "cuda:3",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

mmlu_5shot_bs4_bf16.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394b27758ad95d1194213656be8dec5b8b5222cbfc9a892c81a1cebc7e126793
+size 14328

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54edca3c2a8352c32f3ef03e4f7645332bbc1e4caf9b950ee1c10c4fdbff579f
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9f9ce3f9d7de86e94915298c19be930a279545a20a5086829cec1902a082df
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3a9d5769bd1590e828c3fe7a4711687a5cbc67bc3e6e64532d4d9d911becde
+size 3590488816

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091fdb60b8ee3713df38fd6f9849c3aa82d7eeeb5f6d224a77139543b1db8652
+size 23950

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c83dc4260b41a1c38bb2a26de2ca1f2c7a995aaeea7f1460eda7e0986064d06
+size 1365

truthfulqa_mc_0shot_bs16_bf16.json

@@ -0,0 +1,25 @@
+{
+  "results": {
+    "truthfulqa_mc": {
+      "mc1": 0.2521419828641371,
+      "mc1_stderr": 0.01520152224629996,
+      "mc2": 0.3954683484720209,
+      "mc2_stderr": 0.014883378073318826
+    }
+  },
+  "versions": {
+    "truthfulqa_mc": 1
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
+    "num_fewshot": 0,
+    "batch_size": "16",
+    "batch_sizes": [],
+    "device": "cuda:4",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}

winogrande_5shot_bs16_bf16.json

@@ -0,0 +1,23 @@
+{
+  "results": {
+    "winogrande": {
+      "acc": 0.6511444356748224,
+      "acc_stderr": 0.013395059320137332
+    }
+  },
+  "versions": {
+    "winogrande": 0
+  },
+  "config": {
+    "model": "sparseml",
+    "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
+    "num_fewshot": 5,
+    "batch_size": "16",
+    "batch_sizes": [],
+    "device": "cuda:2",
+    "no_cache": true,
+    "limit": null,
+    "bootstrap_iters": 100000,
+    "description_dict": {}
+  }
+}