commit f5c373863032732f0b16da5a84e09a71b2d1f773 Author: ModelHub XC Date: Mon Apr 13 03:46:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a16 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..2867c7a --- /dev/null +++ b/README.md @@ -0,0 +1,257 @@ +--- +language: +- en +pipeline_tag: text-generation +license: apache-2.0 +license_link: https://www.apache.org/licenses/LICENSE-2.0 +--- + +# Qwen2-1.5B-Instruct-quantized.w8a16 + +## Model Overview +- **Model Architecture:** Qwen2 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** INT8 +- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-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:** 7/2/2024 +- **Version:** 1.0 +- **License(s):** [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) +- **Model Developers:** Neural Magic + +Quantized version of [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct). +It achieves an average score of 55.38 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 55.17. + +### Model Optimizations + +This model was obtained by quantizing the weights of [Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) to INT8 data type. +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 of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT8 and floating point representations of the quantized weights. +[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 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/Qwen2-1.5B-Instruct-quantized.w8a16" +number_gpus = 1 + +sampling_params = SamplingParams(temperature=0.7, top_p=0.8, 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, 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 + +This model is supported by Transformers leveraging the integration with the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) data format. +The following example contemplates how the model can be used using the `generate()` function. + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM + +model_id = "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a16" + +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?"}, +] + +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=0.7, + top_p=0.8, +) +response = outputs[0][input_ids.shape[-1]:] +print(tokenizer.decode(response, skip_special_tokens=True)) +``` + +## Creation + +This model was created by applying the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) library as presented in the code snipet below. +Although AutoGPTQ was used for this particular model, Neural Magic is transitioning to using [llm-compressor](https://github.com/vllm-project/llm-compressor) which supports several quantization schemes and models not supported by AutoGPTQ. + +```python +from transformers import AutoTokenizer +from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig +import random + +model_id = "Qwen/Qwen2-1.5B-Instruct" + +num_samples = 256 +max_seq_len = 8192 + +tokenizer = AutoTokenizer.from_pretrained(model_id) + +max_token_id = len(tokenizer.get_vocab()) - 1 +examples = [] +for _ in range(num_samples): + examples.append( + { + "input_ids": [random.randint(0, max_token_id) for _ in range(max_seq_len)], + "attention_mask": max_seq_len*[1], + } +) + +quantize_config = BaseQuantizeConfig( + bits=8, + group_size=-1, + desc_act=False, + model_file_base_name="model", + damp_percent=0.01, +) + +model = AutoGPTQForCausalLM.from_pretrained( + model_id, + quantize_config, + device_map="auto", +) + +model.quantize(examples) +model.save_pretrained("Qwen2-1.5B-Instruct-quantized.w8a16") +``` + + + +## 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/Qwen2-1.5B-Instruct-quantized.w8a16",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 + Qwen2-1.5B-Instruct + Qwen2-1.5B-Instruct-quantized.w8a16 (this model) + Recovery +
MMLU (5-shot) + 55.65 + 56.08 + 100.8% +
ARC Challenge (25-shot) + 42.83 + 43.09 + 100.6% +
GSM-8K (5-shot, strict-match) + 58.07 + 58.00 + 99.9% +
Hellaswag (10-shot) + 67.43 + 67.44 + 100.0% +
Winogrande (5-shot) + 63.69 + 64.33 + 101.0% +
TruthfulQA (0-shot) + 43.34 + 43.38 + 100.1% +
Average + 55.17 + 55.38 + 100.4% +
diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..409be9f --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,5 @@ +{ + "<|endoftext|>": 151643, + "<|im_end|>": 151645, + "<|im_start|>": 151644 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..37b2a3e --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e893c235d0e4b471cb508b04cb3e0e28452666ff383e34846036b5f56c360fd +size 1306 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..329b7e6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "eos_token_id": 151645, + "transformers_version": "4.42.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..61656c9 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887f0d666be8996106023787674c6534f6c993a3fa0790149b28c2dcea7f3e7d +size 1781306400 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..2c53454 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,20 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..f9d83c4 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1 +size 7028043 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7228de6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f4ae7809a0d555cce69fa8632f03e1294c779f0103df48b2b1f85acb82d1d3 +size 1299 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833