commit 4a61a23f7f807543f77e492073259fe2f47bb2cd Author: ModelHub XC Date: Thu Oct 22 16:53:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/gemma-2-9b-it-quantized.w4a16 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..d9052f6 --- /dev/null +++ b/README.md @@ -0,0 +1,262 @@ +--- +language: +- en +pipeline_tag: text-generation +license: llama2 +--- + +# gemma-2-9b-it-quantized.w4a16 + +## Model Overview +- **Model Architecture:** Gemma-2 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** INT4 +- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-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-2-9b-it](https://huggingface.co/google/gemma-2-9b-it). +It achieves an average score of 73.62 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 73.23. + +### Model Optimizations + +This model was obtained by quantizing the weights of [gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) to INT4 data type. +This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%. + +Only the weights of the linear operators within transformers blocks are quantized. Symmetric group-wise quantization is applied, in which a linear scaling per group maps the INT4 and floating point representations of the quantized weights. +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. Quantization is performed with 1% damping factor, group-size as 128 and 512 sequences sampled from [Open-Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). + +## 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-2-9b-it-quantized.w4a16" + +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? Please respond in pirate speak."}, +] + +prompts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) + +llm = LLM(model=model_id, tensor_parallel_size=2) + +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/gemma-2-9b-it-quantized.w4a16" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype="auto", + device_map="auto", +) + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you? Please respond in pirate speak"}, +] + +input_ids = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_tensors="pt" +).to(model.device) + +terminators = [ + tokenizer.eos_token_id, + tokenizer.convert_tokens_to_ids("<|eot_id|>") +] + +outputs = model.generate( + input_ids, + max_new_tokens=256, + eos_token_id=terminators, + 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 llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot +from llmcompressor.modifiers.quantization import GPTQModifier +from datasets import load_dataset +import random + +model_id = "google/gemma-2-9b-it" + +num_samples = 512 +max_seq_len = 4096 + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +preprocess_fn = lambda example: {"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n{text}".format_map(example)} + +dataset_name = "neuralmagic/LLM_compression_calibration" +dataset = load_dataset(dataset_name, split="train") +ds = dataset.shuffle().select(range(num_samples)) +ds = ds.map(preprocess_fn) + +examples = [ + tokenizer( + example["text"], padding=False, max_length=max_seq_len, truncation=True, + ) for example in ds +] + +recipe = GPTQModifier( + targets="Linear", + scheme="W4A16", + 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("gemma-2-9b-it-quantized.w4a16") +``` + + +## 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-2-9b-it-quantized.w4a16",dtype=auto,tensor_parallel_size=2,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,trust_remote_code=True \ + --tasks openllm \ + --batch_size auto +``` + +### Accuracy + +#### Open LLM Leaderboard evaluation scores + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Benchmark + gemma-2-9b-it + gemma-2-9b-it-quantized.w4a16(this model) + Recovery +
MMLU (5-shot) + 72.28 + 71.36 + 98.72% +
ARC Challenge (25-shot) + 71.5 + 70.98 + 99.27% +
GSM-8K (5-shot, strict-match) + 76.26 + 79.83 + 104.68% +
Hellaswag (10-shot) + 81.91 + 81.29 + 99.24% +
Winogrande (5-shot) + 77.11 + 78.29 + 101.53% +
TruthfulQA (0-shot) + 60.32 + 59.97 + 99.42% +
Average + 73.23 + 73.62 + 100.53% +
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..702834c --- /dev/null +++ b/config.json @@ -0,0 +1,65 @@ +{ + "_name_or_path": "/network/abhinav/models/gemma-2-9b-it", + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 16, + "num_hidden_layers": 42, + "num_key_value_heads": 8, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_theta": 10000.0, + "sliding_window": 4096, + "sliding_window_size": 4096, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.3", + "use_cache": true, + "vocab_size": 256000, + "quantization_config": { + "config_groups": { + "group_0": { + "input_activations": null, + "output_activations": null, + "targets": [ + "Linear" + ], + "weights": { + "block_structure": null, + "dynamic": false, + "group_size": 128, + "num_bits": 4, + "observer": "minmax", + "observer_kwargs": {}, + "strategy": "group", + "symmetric": true, + "type": "int" + } + } + }, + "format": "pack-quantized", + "global_compression_ratio": 1.6699320785908212, + "ignore": [ + "lm_head" + ], + "kv_cache_scheme": null, + "quant_method": "compressed-tensors", + "quantization_status": "compressed", + "sparsity_config": {} + } +} 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..0d66015 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "4.43.3" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..27df8b2 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37299b51354b4cfcc84ddbe440283dc45981a8a1ce17a80be49d978e0f994b24 +size 4977264328 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..3365508 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d06e1d4b08823c04793dc893631501984118336c3a6d3f1885239c2c0bb3ca2 +size 2985942896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..7573303 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6153f8cbefa4194744e45c7865bd4a8037d4bd1c434a5dee2e9d8669dc5b5c75 +size 92455 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..af0eac5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 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