commit 90a7b74025cb4d04edf4b7d2a2ba6b421523037b Author: ModelHub XC Date: Mon Jul 6 07:42:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..588a379 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2dc26a --- /dev/null +++ b/README.md @@ -0,0 +1,257 @@ +--- +language: +- en +pipeline_tag: text-generation +license: llama3 +license_link: https://llama.meta.com/llama3/license/ +--- + +# Meta-Llama-3-8B-Instruct-quantized.w8a16 + +## Model Overview +- **Model Architecture:** Meta-Llama-3 + - **Input:** Text + - **Output:** Text +- **Model Optimizations:** + - **Weight quantization:** INT8 +- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-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):** [Llama3](https://llama.meta.com/llama3/license/) +- **Model Developers:** Neural Magic + +Quantized version of [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct). +It achieves an average score of 68.69 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 68.54. + +### Model Optimizations + +This model was obtained by quantizing the weights of [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-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/Meta-Llama-3-8B-Instruct-quantized.w8a16" +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, 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/Meta-Llama-3-8B-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=0.6, + 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 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 = "meta-llama/Meta-Llama-3-8B-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("Meta-Llama-3-8B-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/Meta-Llama-3-8B-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 + Meta-Llama-3-8B-Instruct + Meta-Llama-3-8B-Instruct-quantized.w8a16(this model) + Recovery +
MMLU (5-shot) + 66.54 + 66.55 + 100.0% +
ARC Challenge (25-shot) + 62.63 + 61.52 + 98.2% +
GSM-8K (5-shot, strict-match) + 75.21 + 75.89 + 100.9% +
Hellaswag (10-shot) + 78.81 + 78.69 + 99.8% +
Winogrande (5-shot) + 76.48 + 76.01 + 98.2% +
TruthfulQA (0-shot) + 52.49 + 52.60 + 100.2% +
Average + 68.69 + 68.54 + 99.8% +
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..ddbfb8f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea6feb101ff8147aedc029b7849cdd22c1148bcd5e7c1f130c44bf2707447039 +size 1327 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..b7b2d7f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": 128009, + "transformers_version": "4.42.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..708fbd3 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a367e5458e24b9769471abede3c0e1a54080ea3415b7d1f82d2b117d4c95742 +size 4986235568 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..61379cf --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9156b4e4168b0dfa3bde1b401e10bfde1079c49c9ae0bf500623727aba0aea89 +size 4104182696 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4398af3 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d9ecd9b34a95ea77722ea41a1844577087a96e076380794596c1ddd412764f +size 78459 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..02ee80b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..9a62752 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7 +size 9085698 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a251eec --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0e3a7cce6e4d787e85eb1c24d548420e0d7fe2c7a214e192795c46e40d75bb +size 50977