commit 97d4cafa7953de447da40406d19e6fb61a6f244a Author: ModelHub XC Date: Sun Apr 19 17:04:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8 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..bf1bfd8 --- /dev/null +++ b/README.md @@ -0,0 +1,259 @@ +--- +language: +- en +pipeline_tag: text-generation +license: mit +base_model: +- microsoft/Phi-3-mini-128k-instruct +--- + +# Phi-3-mini-128k-instruct-quantized.w8a8 + +## Model Overview +- **Model Architecture:** Phi-3 + - **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 [Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct), 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:** 7/11/2024 +- **Version:** 1.0 +- **License(s):** [MIT](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md) +- **Model Developers:** Neural Magic + +Quantized version of [Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct), a 3.8 billion-parameter open model trained using the Phi-3 datasets. +It achieves an average score of 68.74 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 69.18. + +### Model Optimizations + +This model was obtained by quantizing the weights of [Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) 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 of 8,192 random tokens. + +## 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/Phi-3-mini-128k-instruct-quantized.w8a8" +number_gpus = 1 + +sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256) + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] + +prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False) + +llm = LLM(model=model_id, trust_remote_code=True, max_model_len=8196, tensor_parallel_size=number_gpus) + +outputs = llm.generate(prompts, sampling_params) + +generated_text = outputs[0].outputs[0].text +print(generated_text) +``` + + +vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details. + +### Use with transformers + +The following example contemplates how the model can be deployed in Transformers using the `generate()` function. + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM + +model_id = "neuralmagic/Phi-3-mini-128k-instruct-quantized.w8a8" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype="auto", + device_map="auto", + trust_remote_code=True, +) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] + +input_ids = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_tensors="pt" +).to(model.device) + +outputs = model.generate( + input_ids, + max_new_tokens=256, + do_sample=True, + temperature=0.6, + top_p=0.9, +) +response = outputs[0][input_ids.shape[-1]:] +print(tokenizer.decode(response, skip_special_tokens=True)) +``` + +## 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 Dataset +from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot +from llmcompressor.modifiers.quantization import GPTQModifier +import random + +model_id = "microsoft/Phi-3-mini-128k-instruct" + +num_samples = 256 +max_seq_len = 8192 + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +max_token_id = len(tokenizer.get_vocab()) - 1 +input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)] +attention_mask = num_samples * [max_seq_len * [1]] +ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask}) + +recipe = GPTQModifier( + targets="Linear", + scheme="W8A8", + ignore=["lm_head"], + dampening_frac=0.01, +) + +model = SparseAutoModelForCausalLM.from_pretrained( + model_id, + device_map="auto", + trust_remote_code=True, +) + +oneshot( + model=model, + dataset=ds, + recipe=recipe, + max_seq_length=max_seq_len, + num_calibration_samples=num_samples, +) + +model.save_pretrained("Phi-3-mini-128k-instruct-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/Phi-3-mini-128k-instruct-quantized.w8a8",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=1 \ + --tasks openllm \ + --batch_size auto +``` + +### Accuracy + +#### Open LLM Leaderboard evaluation scores + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Benchmark + Phi-3-mini-128k-instruct + Phi-3-mini-128k-instruct-quantized.w8a8 (this model) + Recovery +
MMLU (5-shot) + 68.10 + 67.60 + 99.3% +
ARC Challenge (25-shot) + 63.91 + 62.97 + 98.5% +
GSM-8K (5-shot, strict-match) + 75.59 + 74.83 + 99.0% +
Hellaswag (10-shot) + 79.81 + 78.97 + 98.9% +
Winogrande (5-shot) + 73.72 + 73.72 + 100.0% +
TruthfulQA (0-shot) + 53.94 + 54.34 + 100.7% +
Average + 69.18 + 68.74 + 99.4% +
\ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..c9d3d3a --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,13 @@ +{ + "<|assistant|>": 32001, + "<|endoftext|>": 32000, + "<|end|>": 32007, + "<|placeholder1|>": 32002, + "<|placeholder2|>": 32003, + "<|placeholder3|>": 32004, + "<|placeholder4|>": 32005, + "<|placeholder5|>": 32008, + "<|placeholder6|>": 32009, + "<|system|>": 32006, + "<|user|>": 32010 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..5a333ca --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3102dbb15dd4aa6ec37d0d7a16f793f8350a06eab4c7319f527aac037c374117 +size 4649 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/configuration_phi3.py b/configuration_phi3.py new file mode 100644 index 0000000..6bca687 --- /dev/null +++ b/configuration_phi3.py @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25f57c0823fcb9753880a25e79ab562b039d6187102ac13e4ff26dd11e9a81c +size 11153 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3e38c2e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": [ + 32000, + 32001, + 32007 + ], + "pad_token_id": 32000, + "transformers_version": "4.42.3" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4578fd0 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbadf7d546a0d706ac66072eb341ff27cbd1ea4e7785a6204510873d5eba316 +size 4020349648 diff --git a/modeling_phi3.py b/modeling_phi3.py new file mode 100644 index 0000000..8f55f31 --- /dev/null +++ b/modeling_phi3.py @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9e75b93ed114a3918971224973a8e9dba3d100a50e6363f88c60efb93b18579 +size 73193 diff --git a/recipe.yaml b/recipe.yaml new file mode 100644 index 0000000..8efef86 --- /dev/null +++ b/recipe.yaml @@ -0,0 +1,11 @@ +quant_stage: + quant_modifiers: + GPTQModifier: + sequential_update: false + dampening_frac: 0.01 + ignore: [lm_head] + config_groups: + group_0: + targets: [Linear] + weights: {num_bits: 8, type: int, symmetric: true, strategy: channel} + input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token} diff --git a/results_2024-07-10T00-24-05.100161.json b/results_2024-07-10T00-24-05.100161.json new file mode 100644 index 0000000..78b91ed --- /dev/null +++ b/results_2024-07-10T00-24-05.100161.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:410289ce6de5a19bc10ec24ac71bbc619e24ba4d5c887f883f592229d1d11688 +size 121310 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..50b4d34 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "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..756fd21 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f067e1e15cd0a36ebef3668024882cb67a80b86fb4b7b4b128481f0d474db7 +size 1844436 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..354b16e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b73681cb1ccf981f57b19685152b981b06069dfeedd29749c7050c680ab98cd +size 3341