commit d2e981e581ab2ca8818e1f2a6117df7d2286a13b Author: ModelHub XC Date: Mon May 18 01:00:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/llama2.c-stories110M-pruned50 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..7a34efe --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Xenova/llama2.c-stories110M +inference: true +model_type: llama +quantized_by: mgoin +tags: +- nm-vllm +- sparse +--- + +## llama2.c-stories110M-pruned50 +This repo contains model files for [llama2.c 110M tinystories](https://huggingface.co/Xenova/llama2.c-stories110M) 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/llama2.c-stories110M-pruned50", sparsity="sparse_w16a16") +prompt = "Hello my name is" + +sampling_params = SamplingParams(max_tokens=100, temperature=0) +outputs = model.generate(prompt, sampling_params=sampling_params) +print(outputs[0].outputs[0].text) +``` + +## Prompt template + +N/A + +## 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 = "Xenova/llama2.c-stories110M" +calibration_dataset = "open_platypus" +output_directory = "output/" + +recipe = """ +test_stage: + obcq_modifiers: + SparseGPTModifier: + sparsity: 0.5 + sequential_update: true + 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/config.json b/config.json new file mode 100644 index 0000000..af6dbbd --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "Xenova/llama2.c-stories110M", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 768, + "initializer_range": 0.02, + "intermediate_size": 2048, + "max_position_embeddings": 1024, + "model_type": "llama", + "num_attention_heads": 12, + "num_hidden_layers": 12, + "num_key_value_heads": 12, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": true, + "torch_dtype": "float32", + "transformers_version": "1.7.0.20240304", + "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..16ca0aa --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "1.7.0.20240304" +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..413239b --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cfab11db42972f59bcaa3b5d04209ad63ea62f5e761d67bf9ec8bfca580e62 +size 438156674 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..475606e --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,6 @@ +test_stage: + obcq_modifiers: + SparseGPTModifier: + sparsity: 0.5 + sequential_update: true + targets: ['re:model.layers.\d*$'] diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1e1a997 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c039a17 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a56d209a973f412a09324c5356531df964406197a10945dccf7e7c772be6c37 +size 1842862 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..3ad2a41 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,38 @@ +{ + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 2048, + "pad_token": "", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}