commit 577b19aba0e97a872d133d5873014fe074fe0c93 Author: ModelHub XC Date: Fri Oct 23 20:16:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/starcoder2-3b-FP8 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..3f0b293 --- /dev/null +++ b/README.md @@ -0,0 +1,233 @@ +--- +tags: +- fp8 +- vllm +license: other +license_name: bigcode-openrail-m +license_link: https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement +--- + +# starcoder2-3b-FP8 + +## Model Overview +- **Model Architecture:** starcoder2-3b + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** FP8 + - **Activation quantization:** FP8 +- **Intended Use Cases:** Intended for commercial and research use in English. +- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. +- **Release Date:** 8/1/2024 +- **Version:** 1.0 +- **License(s):** [bigcode-openrail-m](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement) +- **Model Developers:** Neural Magic + +Quantized version of [starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b). + +It achieves an average score of 35.53 on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark, whereas the unquantized model achieves 35.35. + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b) to FP8 data type, ready for inference with vLLM >= 0.5.2. +This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. + +Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-tensor quantization is applied, in which a single linear scaling maps the FP8 representations of the quantized weights and activations. +[AutoFP8](https://github.com/neuralmagic/AutoFP8) is used for quantization with 512 sequences of UltraChat. + + + +## Creation + +This model was created by applying [LLM Compressor with calibration samples from UltraChat](https://github.com/vllm-project/llm-compressor/blob/sa/big_model_support/examples/big_model_offloading/big_model_w8a8_calibrate.py), as presented in the code snipet below. +A slight modification to the code was made due to the parameters of the model. Running the below code will throw an index error, and simply replacing the erroneous line with ```max_quant_shape = param.shape[0]``` resolves the issue. + +```python +import torch +from datasets import load_dataset +from transformers import AutoTokenizer + +from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot +from llmcompressor.transformers.compression.helpers import ( + calculate_offload_device_map, + custom_offload_device_map, +) + +recipe = """ +quant_stage: + quant_modifiers: + QuantizationModifier: + ignore: ["lm_head"] + config_groups: + group_0: + weights: + num_bits: 8 + type: float + strategy: tensor + dynamic: false + symmetric: true + input_activations: + num_bits: 8 + type: float + strategy: tensor + dynamic: false + symmetric: true + targets: ["Linear"] +""" + +model_stub = "bigcode/starcoder2-3b" +model_name = model_stub.split("/")[-1] + +device_map = calculate_offload_device_map( + model_stub, reserve_for_hessians=False, num_gpus=8, torch_dtype=torch.float16 +) + +model = SparseAutoModelForCausalLM.from_pretrained( + model_stub, torch_dtype=torch.float16, device_map=device_map +) +tokenizer = AutoTokenizer.from_pretrained(model_stub) + +output_dir = f"./{model_name}-FP8" + +DATASET_ID = "HuggingFaceH4/ultrachat_200k" +DATASET_SPLIT = "train_sft" +NUM_CALIBRATION_SAMPLES = 512 +MAX_SEQUENCE_LENGTH = 4096 + +ds = load_dataset(DATASET_ID, split=DATASET_SPLIT) +ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES)) + +def preprocess(example): + return { + "text": " ".join([msg["content"] for msg in example["messages"]]) + } + +ds = ds.map(preprocess) + +def tokenize(sample): + return tokenizer( + sample["text"], + padding=False, + max_length=MAX_SEQUENCE_LENGTH, + truncation=True, + add_special_tokens=False, + ) + +ds = ds.map(tokenize, remove_columns=ds.column_names) + +oneshot( + model=model, + output_dir=output_dir, + dataset=ds, + recipe=recipe, + max_seq_length=MAX_SEQUENCE_LENGTH, + num_calibration_samples=NUM_CALIBRATION_SAMPLES, + save_compressed=True, +) +``` + +## Evaluation + +The model was evaluated on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark with the [Neural Magic fork](https://github.com/neuralmagic/evalplus) of the [EvalPlus implementation of HumanEval+](https://github.com/evalplus/evalplus) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command: +``` +python codegen/generate.py --model neuralmagic/starcoder2-3b-FP8 --temperature 0.2 --n_samples 50 --resume --root ~ --dataset humaneval +python evalplus/sanitize.py ~/humaneval/neuralmagic--starcoder2-3b-FP8_vllm_temp_0.2 +evalplus.evaluate --dataset humaneval --samples ~/humaneval/neuralmagic--starcoder2-3b-FP8_vllm_temp_0.2-sanitized +``` + +### Accuracy + +#### HumanEval+ evaluation scores + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Benchmark + starcoder2-3b + starcoder2-3b-FP8(this model) + Recovery +
base pass@1 + 30.7 + 30.8 + 100.3% +
base pass@10 + 44.9 + 45.4 + 101.1% +
base+extra pass@1 + 26.6 + 26.5 + 99.62% +
base+extra pass@10 + 39.2 + 39.4 + 100.5% +
Average + 35.35 + 35.53 + 100.3% +
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..7bb5975 --- /dev/null +++ b/config.json @@ -0,0 +1,70 @@ +{ + "_name_or_path": "/home/linghao/.cache/huggingface/hub/models--bigcode--starcoder2-3b/snapshots/733247c55e3f73af49ce8e9c7949bf14af205928", + "architectures": [ + "Starcoder2ForCausalLM" + ], + "attention_dropout": 0.1, + "bos_token_id": 0, + "embedding_dropout": 0.1, + "eos_token_id": 0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 3072, + "initializer_range": 0.018042, + "intermediate_size": 12288, + "max_position_embeddings": 16384, + "mlp_type": "default", + "model_type": "starcoder2", + "norm_epsilon": 1e-05, + "norm_type": "layer_norm", + "num_attention_heads": 24, + "num_hidden_layers": 30, + "num_key_value_heads": 2, + "residual_dropout": 0.1, + "rope_theta": 999999.4420358813, + "sliding_window": 4096, + "torch_dtype": "float16", + "transformers_version": "4.44.0.dev0", + "use_bias": true, + "use_cache": true, + "vocab_size": 49152, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": { + "block_structure": null, + "dynamic": false, + "group_size": null, + "num_bits": 8, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "tensor", + "symmetric": true, + "type": "float" + }, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "block_structure": null, + "dynamic": false, + "group_size": null, + "num_bits": 8, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "tensor", + "symmetric": true, + "type": "float" + } + } + }, + "format": "naive-quantized", + "global_compression_ratio": 1.4225351755647873, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed" + } +} 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..119bbdb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 0, + "transformers_version": "4.44.0.dev0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..966b9fd --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9dfb2c5bd3b10bd46aa7fdaa8c54e8e1bcfe1618d9288320ebc82c518442fc +size 441705 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..ec728db --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afffc343654caa0afece610ab84d61a322ee6850b29841b24e4bc801556ada70 +size 3484485728 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..47f6012 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,10 @@ +quant_stage: + quant_modifiers: + QuantizationModifier: + ignore: [lm_head] + config_groups: + group_0: + weights: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true} + input_activations: {num_bits: 8, type: float, strategy: tensor, dynamic: false, + symmetric: true} + targets: [Linear] diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8d8f8dd --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8d9e1e1efd775a22a19ee45b85a31b524766c0db89de00ed249a7433794762 +size 1332 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..16c4611 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17fa145258b20c18287f1e3bd804e074cc13333f11984a2f5a2f11c5110437aa +size 2060947 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a33707a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967231a56db74a08ced2afea94492b831e581da94a411436cce9ec40a0541f00 +size 7909 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..56972d7 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542ee3f8b27b3a825754728b4dc59eff31065fecce843a93f09b98f13dbd7de9 +size 777202