commit 708eede362d209a2a8fafcf699ad9f8762332463 Author: ModelHub XC Date: Sat Jun 27 21:08:12 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_50 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..9846175 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: neuralmagic/Llama-2-7b-pruned50-retrained +inference: true +model_type: llama +pipeline_tag: text-generation +datasets: + - cerebras/SlimPajama-627B + - theblackcat102/evol-codealpaca-v1 +tags: +- sparse +- code +--- + +# Llama-2-7b-pruned50-retrained-evolcodealpaca + +This repo contains a [50% sparse Llama 2 7B](https://huggingface.co/neuralmagic/Llama-2-7b-pruned50-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-pruned50-retrained-evolcodealpaca") +model = AutoModelForCausalLM.from_pretrained("neuralmagic/Llama-2-7b-pruned50-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-pruned50-retrained-evolcodealpaca | +|------------------------------------------------|---------------|-------------|-------------------------------| +| [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 32.03 | 38.15 | + +## Model Training Details + +This model was obtained by sparse-tranfer 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. +Training was perfomerd for 2 epochs and used 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..001b06f --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "neuralmagic/Llama-2-7b-pruned50-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..4ee8533 --- /dev/null +++ b/humaneval_fp16.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877ec6bd95d765e7fbadd85655b161370a17138a613814e82400c58d67cc72a9 +size 1491 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..fa95f9f --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184a7dbb9d6dd5dda7364519c5c5d62d354aeb0c8dcbd2b9bff328e34a170c81 +size 4938985352 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..590fc7d --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dcf450d4603fa17fa73f9d8cd107239ed5436b23f6a310c2efaaf96584f1cc8 +size 4947390880 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..f151dc6 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7b268010672b6c6db49ee36a8a357fab231b171b67d3732707c130cc28a144 +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..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_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..120fe80 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,41 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}