commit a8d5347d0ca4e8b084133873fb9287da38338154 Author: ModelHub XC Date: Thu Jul 2 07:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Llama-2-7b-evol-code-alpaca-pruned_70 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..da4584b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: neuralmagic/Llama-2-7b-pruned70-retrained +inference: true +model_type: llama +pipeline_tag: text-generation +datasets: + - cerebras/SlimPajama-627B + - theblackcat102/evol-codealpaca-v1 +tags: +- sparse +- code +--- + +# Llama-2-7b-pruned70-retrained-evolcodealpaca + +This repo contains a [70% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned70-retrained) finetuned for code generation tasks using the [Evolved CodeAlpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) 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-evolcodealpaca") +model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned70-retrained-evolcodealpaca", device_map="auto") + +input_text = "def fibonacci(n):\n" +input_ids = tokenizer(input_text, 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-evolcodealpaca | Llama-2-7b-pruned70-retrained-evolcodealpaca | +|------------------------------------------------|---------------|-------------|-------------------------------| +| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 32.03 | 36.3 | + +## Model Training Details + +This model was obtained by gradual sparse-transfer of the sparse foundational model [Llama-2-7b-pruned50-retrained](https://huggingface.co/neuralmagic/Llama-2-7b-pruned50-retrained) on 60% of the [evolcodealpaca](https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1) dataset. +The 50% sparse foundational model was finetuned for 2 epochs and then pruned to 70% sparsity using [SparseGPT](https://arxiv.org/abs/2301.00774). Then, the model was finetuned for 1 more epoch with the [SquareHead](https://arxiv.org/abs/2310.06927) knowledge distillation with [Llama-2-7b-evolcodealpaca](https://huggingface.co/neuralmagic/Llama-2-7b-evolcodealpaca) 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) diff --git a/config.json b/config.json new file mode 100644 index 0000000..3ed3574 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "neuralmagic/Llama-2-7b-pruned70-retrained-evolcodealpaca", + "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": "4.39.3", + "use_cache": true, + "vocab_size": 32000 +} 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..b8e05e6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.39.3" +} diff --git a/humaneval_fp16.json b/humaneval_fp16.json new file mode 100644 index 0000000..6622c0f --- /dev/null +++ b/humaneval_fp16.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e1244d18c60e9231a502c9957ff352bb0b5c35182d40c1c9ab15fc9799b789 +size 1541 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..a6772b0 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f324c1d481b1538dd9b8573ee3a39200b7b7eeb679ac5fd757e2385ee3feb3 +size 4938985352 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..635534e --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6925642cbd5d212d15e196c382daede5143061454c9ff505de45d934aca2ca98 +size 4947390880 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..0cd897b --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59debb66c27eee4873a1a82021023898e64941334f0fe656808369b7cada8c4 +size 3590488816 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..b3d8d7d --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091fdb60b8ee3713df38fd6f9849c3aa82d7eeeb5f6d224a77139543b1db8652 +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5472e7d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55acd0f7c82d279b20ca5198af105372b1ea25292b4a42dfd27043e889ce3ae6 +size 1842866 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a5d4264 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ecc606ae2a9cefdd5435d5d301663f5f61d5b3d5a8e030c9666c32a8ae5ca6 +size 1029