模型:
h2oai/h2ogpt-oasst1-512-12b
H2O.ai的h2ogpt-oasst1-512-12b是一种拥有120亿参数的大型语言模型,可用于商业用途。
要在带有GPU的计算机上使用transformers库和accelerate库与模型一起使用,首先确保已安装这些库。
pip install transformers==4.28.1
pip install accelerate==0.18.0
import torch
from transformers import pipeline
generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-12b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type='human_bot')
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
或者,如果您不想使用trust_remote_code=True,可以下载 instruct_pipeline.py ,将其与笔记本放在一起,并从加载的模型和分词器构建自己的流水线:
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oasst1-512-12b", torch_dtype=torch.bfloat16, device_map="auto")
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type='human_bot')
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
GPTNeoXForCausalLM(
(gpt_neox): GPTNeoXModel(
(embed_in): Embedding(50688, 5120)
(layers): ModuleList(
(0-35): 36 x GPTNeoXLayer(
(input_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
(post_attention_layernorm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
(attention): GPTNeoXAttention(
(rotary_emb): RotaryEmbedding()
(query_key_value): Linear(in_features=5120, out_features=15360, bias=True)
(dense): Linear(in_features=5120, out_features=5120, bias=True)
)
(mlp): GPTNeoXMLP(
(dense_h_to_4h): Linear(in_features=5120, out_features=20480, bias=True)
(dense_4h_to_h): Linear(in_features=20480, out_features=5120, bias=True)
(act): GELUActivation()
)
)
)
(final_layer_norm): LayerNorm((5120,), eps=1e-05, elementwise_affine=True)
)
(embed_out): Linear(in_features=5120, out_features=50688, bias=False)
)
GPTNeoXConfig {
"_name_or_path": "h2oai/h2ogpt-oasst1-512-12b",
"architectures": [
"GPTNeoXForCausalLM"
],
"bos_token_id": 0,
"classifier_dropout": 0.1,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 0,
"hidden_act": "gelu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 20480,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 40,
"num_hidden_layers": 36,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50688
}
使用 EleutherAI lm-evaluation-harness 进行的模型验证结果。
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
arc_challenge | 0 | acc | 0.3157 | ± | 0.0136 |
acc_norm | 0.3507 | ± | 0.0139 | ||
arc_easy | 0 | acc | 0.6932 | ± | 0.0095 |
acc_norm | 0.6225 | ± | 0.0099 | ||
boolq | 1 | acc | 0.6685 | ± | 0.0082 |
hellaswag | 0 | acc | 0.5140 | ± | 0.0050 |
acc_norm | 0.6803 | ± | 0.0047 | ||
openbookqa | 0 | acc | 0.2900 | ± | 0.0203 |
acc_norm | 0.3740 | ± | 0.0217 | ||
piqa | 0 | acc | 0.7682 | ± | 0.0098 |
acc_norm | 0.7661 | ± | 0.0099 | ||
winogrande | 0 | acc | 0.6369 | ± | 0.0135 |
在使用本存储库提供的大型语言模型之前,请仔细阅读此免责声明。您使用该模型即表示您同意以下条款和条件。
通过使用此存储库提供的大型语言模型,您同意接受并遵守本免责声明中概述的条款和条件。如果您不同意本免责声明的任何部分,您应该避免使用该模型和由其生成的任何内容。