h2oGPT 模型卡片

from openmind import pipeline, is_torch_npu_available
from openmind_hub import snapshot_download

if is_torch_npu_available():
	device = "npu:0"
else:
	device = "cpu"
generate_text = pipeline(
        model="SY_AICC/h2ogpt-oig-oasst1-256-6_9b",
        torch_dtype=torch.bfloat16, 
        trust_remote_code=True,
        device=device)
output = generate_text(
        "Why is drinking water so healthy?", 
        max_new_tokens=100)
print(res[0]["generated_text"])

GPTNeoXForCausalLM(
  (gpt_neox): GPTNeoXModel(
    (embed_in): Embedding(50432, 4096)
    (layers): ModuleList(
      (0-31): 32 x GPTNeoXLayer(
        (input_layernorm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
        (post_attention_layernorm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
        (attention): GPTNeoXAttention(
          (rotary_emb): RotaryEmbedding()
          (query_key_value): Linear(in_features=4096, out_features=12288, bias=True)
          (dense): Linear(in_features=4096, out_features=4096, bias=True)
        )
        (mlp): GPTNeoXMLP(
          (dense_h_to_4h): Linear(in_features=4096, out_features=16384, bias=True)
          (dense_4h_to_h): Linear(in_features=16384, out_features=4096, bias=True)
          (act): GELUActivation()
        )
      )
    )
    (final_layer_norm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
  )
  (embed_out): Linear(in_features=4096, out_features=50432, bias=False)
)

GPTNeoXConfig {
  "_name_or_path": "h2oai/h2ogpt-oig-oasst1-256-6_9b",
  "architectures": [
    "GPTNeoXForCausalLM"
  ],
  "bos_token_id": 0,
  "custom_pipelines": {
    "text-generation": {
      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
      "pt": "AutoModelForCausalLM"
    }
  },
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 16384,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neox",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.1",
  "use_cache": true,
  "use_parallel_residual": true,
  "vocab_size": 50432
}