commit eea7f4f8dca6be9179bbdc3540a7933924f2ec29 Author: ModelHub XC Date: Sat Apr 25 20:19:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/gemma-2-2b-it-quantized.w8a8 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a2c584 --- /dev/null +++ b/README.md @@ -0,0 +1,214 @@ +--- +pipeline_tag: text-generation +tags: +- int8 +- vllm +license: gemma +base_model: google/gemma-2-2b-it +--- + +# gemma-2-2b-it-quantized.w8a8 + +## Model Overview +- **Model Architecture:** Gemma 2 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Activation quantization:** INT8 + - **Weight quantization:** INT8 +- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it), this models is intended for assistant-like chat. +- **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:** 8/16/2024 +- **Version:** 1.0 +- **License(s):** [gemma](https://ai.google.dev/gemma/terms) +- **Model Developers:** Neural Magic + +Quantized version of [gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it). +It achieves an average score of 58.39 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 59.01. + +### Model Optimizations + +This model was obtained by quantizing the weights of [gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) to INT8 data type. +This optimization reduces the number of bits used to represent weights and activations from 16 to 8, reducing GPU memory requirements (by approximately 50%) and increasing matrix-multiply compute throughput (by approximately 2x). +Weight quantization also reduces disk size requirements by approximately 50%. + +Only weights and activations of the linear operators within transformers blocks are quantized. +Weights are quantized with a symmetric static per-channel scheme, where a fixed linear scaling factor is applied between INT8 and floating point representations for each output channel dimension. +Activations are quantized with a symmetric dynamic per-token scheme, computing a linear scaling factor at runtime for each token between INT8 and floating point representations. +The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library. +GPTQ used a 1% damping factor and 256 sequences sequences taken from Neural Magic's [LLM compression calibration dataset](https://huggingface.co/datasets/neuralmagic/LLM_compression_calibration). + +## Deployment + +### Use with vLLM + +This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below. + +```python +from vllm import LLM, SamplingParams +from transformers import AutoTokenizer + +model_id = "neuralmagic/gemma-2-2b-it-quantized.w8a8" + +sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256) + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +messages = [ + {"role": "user", "content": "Who are you? Please respond in pirate speak!"}, +] + +prompts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) + +llm = LLM(model=model_id) + +outputs = llm.generate(prompts, sampling_params) + +generated_text = outputs[0].outputs[0].text +print(generated_text) +``` + +vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +## Creation + +This model was created by using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library as presented in the code snipet below. + +```python +from transformers import AutoTokenizer +from datasets import load_dataset +from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot +from llmcompressor.modifiers.quantization import GPTQModifier + +model_id = "google/gemma-2-2b-it" + +num_samples = 256 +max_seq_len = 8192 + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +def preprocess_fn(example): + return {"text": tokenizer.apply_chat_template(example["messages"], add_generation_prompt=False, tokenize=False)} + +ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train") +ds = ds.shuffle().select(range(num_samples)) +ds = ds.map(preprocess_fn) + +recipe = GPTQModifier( + targets="Linear", + scheme="W8A8", + ignore=["lm_head"], + dampening_frac=0.01, +) + +model = SparseAutoModelForCausalLM.from_pretrained( + model_id, + device_map="auto", +) + +oneshot( + model=model, + dataset=ds, + recipe=recipe, + max_seq_length=max_seq_len, + num_calibration_samples=num_samples, +) +model.save_pretrained("gemma-2-2b-it-quantized.w8a8") +``` + +## Evaluation + +The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/383bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command: +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/gemma-2-2b-it-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \ + --tasks openllm \ + --batch_size auto +``` + +### Accuracy + +#### Open LLM Leaderboard evaluation scores + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Benchmark + gemma-2-2b-it + gemma-2-2b-it-quantized.w8a8 (this model) + Recovery +
MMLU (5-shot) + 56.94 + 56.64 + 99.5% +
ARC Challenge (25-shot) + 58.87 + 56.74 + 96.4% +
GSM-8K (5-shot, strict-match) + 44.81 + 43.97 + 98.1% +
Hellaswag (10-shot) + 71.41 + 71.18 + 99.7% +
Winogrande (5-shot) + 68.82 + 68.59 + 99.7% +
TruthfulQA (0-shot) + 53.22 + 53.19 + 100.0% +
Average + 59.01 + 58.39 + 98.9% +
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..8ee3746 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6866f5f8969485094751e9ee4dcee9ba6f011470ca7632d25de09f86783bb45a +size 1986 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..0712724 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": [ + 1, + 107 + ], + "pad_token_id": 0, + "transformers_version": "4.44.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..30386da --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536db26e9431f4527555085b43be9facc41e0afe939879f2d1fbcaeb9ab8cdd1 +size 4385522016 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..a9d4aa2 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,8 @@ +quant_stage: + quant_modifiers: + GPTQModifier: + sequential_update: false + dampening_frac: 0.01 + ignore: [lm_head] + scheme: W8A8 + targets: Linear diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..8d6368f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "", + "" + ], + "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..4cb5a26 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e79abe26df05a5549e8622f80f25374f6ba306d56cc13915950e9b58a721211 +size 17525456 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..796efe9 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9861e05 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb32b7929c62608d46572e813112b3ad8a841fb98fdd6a4da8559e368a951c89 +size 46996