h2oGPT 模型卡片

from openmind import is_torch_npu_available,AutoModelForCausalLM, AutoTokenizer
from openmind_hub import snapshot_download
from transformers import GPTNeoXTokenizerFast


if is_torch_npu_available():
  device = "npu:0"
else:
  device = "cpu"
tokenizer = GPTNeoXTokenizerFast.from_pretrained("SY_AICC/h2ogpt-oasst1-512-12b",trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
  "SY_AICC/h2ogpt-oasst1-512-12b"
  torch_dtype=torch.bfloat16,
  trust_remote_code=True)
model = model.to(device)
model = model.eval()
inputs = tokenizer(
  "Why is drinking water so healthy?",
  return_tensors="pt").to(device)
pred = model.generate(
  **inputs,
  max_new_tokens=64,
  repetition_penalty=1.1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))

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
}