From 82d6cc0ff3b20608c4d8e14863c1a2efbc6c7a3f Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 20 Sep 2026 06:53:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: RedHatAI/Meta-Llama-3.1-8B-FP8 Source: Original Platform --- .gitattributes | 35 ++++ README.md | 324 +++++++++++++++++++++++++++++++ config.json | 3 + configuration.json | 1 + generation_config.json | 9 + model-00001-of-00002.safetensors | 3 + model-00002-of-00002.safetensors | 3 + model.safetensors.index.json | 3 + recipe.yaml | 10 + special_tokens_map.json | 17 ++ tokenizer.json | 3 + tokenizer_config.json | 3 + 12 files changed, 414 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00002.safetensors create mode 100644 model-00002-of-00002.safetensors create mode 100644 model.safetensors.index.json create mode 100644 recipe.yaml create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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..be8cf41 --- /dev/null +++ b/README.md @@ -0,0 +1,324 @@ +--- +tags: +- fp8 +- vllm +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +pipeline_tag: text-generation +license: llama3.1 +base_model: meta-llama/Meta-Llama-3.1-8B +--- + +# Meta-Llama-3.1-8B-FP8 + +## Model Overview +- **Model Architecture:** Meta-Llama-3.1 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** FP8 + - **Activation quantization:** FP8 +- **Intended Use Cases:** Intended for commercial and research use in multiple languages. Similarly to [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B), this model serves as a base version. +- **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:** 7/23/2024 +- **Version:** 1.0 +- **License(s):** [llama3.1](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE) +- **Model Developers:** Neural Magic + +Quantized version of [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B). +It achieves an average score of 65.90 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 66.47. + +### Model Optimizations + +This model was obtained by quantizing the weights and activations of [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) to FP8 data type, ready for inference with vLLM built from source. +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. +[LLM Compressor](https://github.com/vllm-project/llm-compressor) 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. + +```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 = "meta-llama/Meta-Llama-3.1-8B" +model_name = model_stub.split("/")[-1] + +device_map = calculate_offload_device_map( + model_stub, reserve_for_hessians=False, num_gpus=1, 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": tokenizer.apply_chat_template( + example["messages"], + tokenize=False, + ) + } + +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 MMLU, ARC-Challenge, GSM-8K, Hellaswag, Winogrande and TruthfulQA. +Evaluation was conducted using the Neural Magic fork of [lm-evaluation-harness](https://github.com/neuralmagic/lm-evaluation-harness/tree/llama_3.1_instruct) (branch llama_3.1_instruct) and the [vLLM](https://docs.vllm.ai/en/stable/) engine. +This version of the lm-evaluation-harness includes versions of ARC-Challenge that matches the prompting style of [Meta-Llama-3.1-evals](https://huggingface.co/datasets/meta-llama/Meta-Llama-3.1-8B-evals). + +### Accuracy + +#### Open LLM Leaderboard evaluation scores + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Benchmark + Meta-Llama-3.1-8B + Meta-Llama-3.1-8B-FP8(this model) + Recovery +
MMLU (5-shot) + 65.19 + 65.01 + 99.72% +
ARC Challenge (25-shot) + 78.84 + 77.73 + 98.59% +
GSM-8K (5-shot, strict-match) + 50.34 + 48.82 + 96.98% +
Hellaswag (10-shot) + 82.33 + 81.96 + 99.55% +
Winogrande (5-shot) + 77.98 + 78.06 + 100.10% +
TruthfulQA (0-shot, mc2) + 44.14 + 43.83 + 99.30% +
Average + 66.47 + 65.90 + 99.14% +
+ +### Reproduction + +The results were obtained using the following commands: + +#### MMLU +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks mmlu \ + --num_fewshot 5 \ + --batch_size auto +``` + +#### ARC-Challenge +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks arc_challenge_llama_3.1_instruct \ + --num_fewshot 25 \ + --batch_size auto +``` + +#### GSM-8K +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks gsm8k \ + --num_fewshot 5 \ + --batch_size auto +``` + +#### Hellaswag +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks hellaswag \ + --num_fewshot 10 \ + --batch_size auto +``` + +#### Winogrande +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks winogrande \ + --num_fewshot 5 \ + --batch_size auto +``` + +#### TruthfulQA +``` +lm_eval \ + --model vllm \ + --model_args pretrained="neuralmagic/Meta-Llama-3.1-8B-FP8",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks truthfulqa \ + --num_fewshot 0 \ + --batch_size auto +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..106c2da --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b46401dbc3fd472f8ee7e8d3542612ddce8b78444579b09c6d9a6961f23a6a +size 1996 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..698218a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.44.0.dev0" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..0165762 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baacb8c9c7ce72c18793878de031f78bcb7823262feb545c3e8f91f583a25694 +size 4997856968 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..b15f087 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634211f6adc225cfdbc022a191b362067ef1965547ffed04dd3dd45487b1be20 +size 4083429528 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..65ca930 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff870845b3d0ed7b0048fcb1f6bdfcc42c3db56ea3374697449d66281f166ce2 +size 62753 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..04829af --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|end_of_text|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..66cd9d7 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4 +size 9085657 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ecca21d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a800da9323f6bc65b8a87ae3d209f46a18eb09cf381b6c416551d30372cf1ce6 +size 50534