import torch
import re
import numpy as np
from typing import List, Tuple, Dict, Any
from transformers import (
AutoTokenizer,
PreTrainedModel,
AutoConfig,
LlamaForCausalLM,
GenerationConfig
)
import torch.nn as nn
from tqdm import tqdm
from collections import defaultdict
import pandas as pd
# --------------------------
# 1. 常量与预处理函数（采用新的数据处理方式）
# --------------------------
VALID_ELEMENTS = ["C", "N", "P", "O", "S", "Si", "I", "H", "Cl", "F", "Br", "B", "Se", "Fe", "Co", "As", "K", "Na"]
element_to_idx = {elem: idx for idx, elem in enumerate(VALID_ELEMENTS)}
CHEM_FORMULA_SIZE = r"([A-Z][a-z]*)([0-9]*)"
# 新增的分子公式解析函数
def parse_chem_formula(formula):
pattern = r'([A-Z][a-z]?)(\d*)'
matches = re.findall(pattern, formula)
element_counts = defaultdict(int)
for (element, count) in matches:
count = int(count) if count else 1
element_counts[element] += count
return element_counts
def generate_element_list(formula):
element_counts = parse_chem_formula(formula)
elements = []
for element, count in element_counts.items():
# 跳过氢元素
if element != "H":
elements.extend([element] * count)
return ''.join(elements)
# 化学式转密集向量
def formula_to_dense(chem_formula: str) -> torch.Tensor:
dense_vec = torch.zeros(len(VALID_ELEMENTS), dtype=torch.float32)
matches = re.findall(CHEM_FORMULA_SIZE, chem_formula)
for chem_symbol, num_str in matches:
num = 1 if num_str == "" else int(num_str)
if chem_symbol in element_to_idx:
idx = element_to_idx[chem_symbol]
dense_vec[idx] += num
return dense_vec
# 位置编码生成 (PyTorch实现)
def positional_encoding(max_position: int, d_model: int, min_freq: float = 1e-4) -> torch.Tensor:
position = torch.arange(max_position).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2) * (-torch.log(torch.tensor(min_freq)) / d_model))
pos_enc = torch.zeros(max_position, d_model)
pos_enc[:, 0::2] = torch.sin(position * div_term)
pos_enc[:, 1::2] = torch.cos(position * div_term)
return pos_enc
# 初始化位置编码矩阵
P = positional_encoding(2000000, 254)
dimn = 254 # 与位置编码维度一致
# 质谱数据编码 - 优化短数据处理：仅截断过长数据，不填充短数据
def encode_spectra(rag_tensor: list, P: torch.Tensor, dimn: int) -> list: # 返回列表而非堆叠张量
encoded_list = []
max_len = 501 # 仅对过长数据截断，不强制填充短数据
for sample in rag_tensor:
mz_list, intensity_list = sample
# 创建基础特征矩阵 [m/z, intensity]
base_features = torch.tensor([mz_list, intensity_list], dtype=torch.float32).T
# 添加位置编码特征（保留原始m/z的位置信息）
pos_enc = torch.stack([P[min(int(mz), P.size(0)-1)] for mz in mz_list])
# 组合所有特征 [m/z, intensity, pos_enc...]
features = torch.cat([base_features, pos_enc], dim=1)
# 仅截断过长数据，短数据保持原始长度（不填充）
if features.size(0) > max_len:
features = features[:max_len]
encoded_list.append(features) # 保留原始长度特征
return encoded_list
# 质谱数据预处理 - 确保短数据完整保留
def preprocess_spectra_for_inference(spectrum_str: str, total_mass: float) -> list:
# 解析质谱字符串
pairs = spectrum_str.split()
mz_list, intensity_list = [], []
for pair in pairs:
mz, intensity = pair.split(':')
mz_list.append(float(mz))
intensity_list.append(float(intensity))
# 对于仅含一组数据的情况，额外保留原始精度（不四舍五入）
if len(pairs) == 1:
# 保留原始精度，不进行四舍五入
mz_list = [float(mz) for mz, _ in [pair.split(':') for pair in pairs]]
intensity_list = [float(intensity) for _, intensity in [pair.split(':') for pair in pairs]]
# 添加总精确质量（作为补充特征，不影响原始数据长度）
mz_list.append(total_mass)
intensity_list.append(0.0)
# 仅对长数据进行四舍五入，短数据保留更多精度
if len(mz_list) > 5: # 数据较长时才简化
mz_list = [round(mz, 2) for mz in mz_list]
intensity_list = [round(intensity, 2) for intensity in intensity_list]
return [[mz_list, intensity_list]]
# --------------------------
# 2. 模型类定义（保持结构，采用新实现）
# --------------------------
from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.generation.utils import GenerationMixin
class LlamaWithEncoder(PreTrainedModel, GenerationMixin):
config_class = AutoConfig
_no_split_modules = ["LlamaDecoderLayer", "TransformerEncoderLayer"]
def __init__(self, config, base_model=None, encoder1_dim=18, encoder2_dim=256, hidden_dim=512):
# 添加config属性
self.config = config
super().__init__(self.config)
# 如果未提供base_model，则从config初始化
if base_model is None:
self.model = LlamaForCausalLM(config)
else:
self.model = base_model
# 第一个Transformer Encoder（处理分子式向量）
encoder1_layer = nn.TransformerEncoderLayer(
d_model=encoder1_dim,
nhead=3,
dim_feedforward=hidden_dim,
batch_first=True
)
self.encoder1 = nn.TransformerEncoder(encoder1_layer, num_layers=2)
# 第二个Transformer Encoder（处理质谱矩阵）
encoder2_layer = nn.TransformerEncoderLayer(
d_model=encoder2_dim,
nhead=4,
dim_feedforward=hidden_dim,
batch_first=True
)
self.encoder2 = nn.TransformerEncoder(encoder2_layer, num_layers=2)
# 投影层：将编码器输出映射到模型隐藏层维度
self.proj1 = nn.Linear(encoder1_dim, base_model.config.hidden_size)
self.proj2 = nn.Linear(encoder2_dim, base_model.config.hidden_size)
# 嵌入层（复制基础模型权重但不共享）
self.embed_tokens = nn.Embedding(
num_embeddings=base_model.config.vocab_size,
embedding_dim=base_model.config.hidden_size,
padding_idx=base_model.config.pad_token_id
)
self.embed_tokens.weight.data = base_model.get_input_embeddings().weight.data.clone()
# 必要接口实现
def get_input_embeddings(self):
return self.embed_tokens
def set_input_embeddings(self, value):
self.embed_tokens = value
def get_output_embeddings(self):
return self.model.get_output_embeddings()
def set_output_embeddings(self, new_embeddings):
self.model.set_output_embeddings(new_embeddings)
def get_base_model(self):
return self.model
def forward(
self,
input_ids=None,
attention_mask=None,
encoder1_inputs=None,
encoder2_inputs=None,
labels=None,
past_key_values=None,
output_attentions=None,
output_hidden_states=None,
return_dict=None,** kwargs
) -> CausalLMOutputWithPast:
# 1. 编码器处理
# 分子式编码器输出
enc1_out = self.encoder1(encoder1_inputs) # (batch_size, 1, 18)
enc1_out = enc1_out.mean(dim=1) # (batch_size, 18)
enc1_proj = self.proj1(enc1_out) # (batch_size, hidden_size)
# 质谱编码器输出
enc2_out = self.encoder2(encoder2_inputs) # (batch_size, seq_len, 256)
enc2_out = enc2_out.mean(dim=1) # (batch_size, 256)
enc2_proj = self.proj2(enc2_out) # (batch_size, hidden_size)
# 合并编码器输出（用于替换<mask>）
mask_replacement = (enc1_proj + enc2_proj) / 2 # (batch_size, hidden_size)
# 2. 获取原始嵌入（避免inplace，全程用新张量）
embeddings = self.embed_tokens(input_ids) # (batch_size, seq_len, hidden_size)
batch_size, seq_len, hidden_size = embeddings.size()
# 3. 替换<mask> token（第三个token，索引=2）：用拼接替代inplace赋值
if seq_len > 2:
mask_embed = mask_replacement.unsqueeze(1) # (batch_size, 1, hidden_size)
# 拆分张量并拼接（前2个token + 替换的mask_embed + 剩余token）
part1 = embeddings[:, :2, :] # (batch_size, 2, hidden_size)
part2 = mask_embed # (batch_size, 1, hidden_size)
part3 = embeddings[:, 3:, :] # (batch_size, seq_len-3, hidden_size)
# 拼接为新张量（无inplace操作）
new_embeddings = torch.cat([part1, part2, part3], dim=1) # (batch_size, seq_len, hidden_size)
else:
new_embeddings = embeddings # 序列过短时直接使用原始嵌入
# 4. 调用基础模型
return self.model(
inputs_embeds=new_embeddings,
attention_mask=attention_mask,
labels=labels,
past_key_values=past_key_values,
output_attentions=output_attentions,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
def prepare_inputs_for_generation(self, input_ids, **kwargs):
return {
"input_ids": input_ids,
"attention_mask": kwargs.get("attention_mask", None),
"encoder1_inputs": kwargs.get("encoder1_inputs", None),
"encoder2_inputs": kwargs.get("encoder2_inputs", None),
}
def _get_generation_device(self):
return next(self.parameters()).device
# --------------------------
# 3. 加载模型和Tokenizer（修复核心错误）
# --------------------------
model_path = "./llama3.2-SELFIES" # 模型保存路径
# 加载分词器
tokenizer = AutoTokenizer.from_pretrained(model_path)
# 确保mask token存在
if tokenizer.mask_token is None:
tokenizer.add_special_tokens({"mask_token": "<mask>"})
# 加载模型配置
config = AutoConfig.from_pretrained(model_path)
# 设备配置（优先使用GPU）
device = "cuda:0" if torch.cuda.is_available() else "cpu"
# 修复：先加载基础模型，再传入自定义模型
base_model = LlamaForCausalLM.from_pretrained(
model_path,
config=config,
torch_dtype=torch.bfloat16, # 确保基础模型为bfloat16精度
device_map=device
)
# 使用基础模型初始化自定义模型
model = LlamaWithEncoder(
config=config,
base_model=base_model,
encoder1_dim=18,
encoder2_dim=256,
hidden_dim=512
)
model = model.to(device) # 先转移到设备
model.eval() # 推理模式
# --------------------------
# 4. 推理函数（适配新的数据处理方式）
# --------------------------
def generate_selfies(
formula: str,
spectrum_str: str,
total_mass: float,
max_length: int = 512,
temperature: float = 0.7,
top_p: float = 0.9
) -> str:
"""生成SELFIES字符串"""
model_device = next(model.parameters()).device
# 1. 生成element_list
element_list = generate_element_list(formula)
# 2. 处理分子式向量
formula_vec = formula_to_dense(formula).unsqueeze(0).unsqueeze(0) # (1,1,18)
formula_vec = formula_vec.to(model_device, dtype=torch.bfloat16)
# 3. 处理质谱数据（使用新的预处理和编码方式）
spectra_data = preprocess_spectra_for_inference(spectrum_str, total_mass)
spec_encoded = encode_spectra(spectra_data, P, dimn) # 得到列表形式的编码结果
spec_matrix = spec_encoded[0].to(model_device, dtype=torch.bfloat16).unsqueeze(0) # 添加批次维度
# 4. 构造输入提示
prompt = f"<｜User｜><s><｜Spectrum｜>{element_list}</s>"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model_device)
attention_mask = torch.ones_like(input_ids).to(model_device)
# 5. 模型生成
with torch.no_grad(): # 关闭梯度计算
outputs = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
encoder1_inputs=formula_vec, # 分子式特征
encoder2_inputs=spec_matrix, # 质谱特征
max_length=max_length,
temperature=temperature,
top_p=top_p,
)
# 6. 解码生成结果（去除特殊token）
generated = tokenizer.decode(outputs[0], skip_special_tokens=False)
return generated
# --------------------------
# 5. 推理示例
# --------------------------
if __name__ == "__main__":
# 示例输入
example_formula = "C9H9N3O2S2" # 分子式
example_spectrum_str = "256.0153:100.000000" # mz:intensity格式
example_total_mass = 255.0136185 # 总精确质量
# 生成SELFIES
result = generate_selfies(
formula=example_formula,
spectrum_str=example_spectrum_str,
total_mass=example_total_mass,
max_length=512,
temperature=0.7,
top_p=0.95
)
print("生成的SELFIES字符串：")
print(result)修改代码，解决问题Some weights of LlamaForCausalLM were not initialized from the model checkpoint at ./llama3.2-SELFIES and are newly initialized: ['lm_head.weight', 'model.embed_tokens.weight', 'model.layers.0.input_layernorm.weight', 'model.layers.0.mlp.down_proj.weight', 'model.layers.0.mlp.gate_proj.weight', 'model.layers.0.mlp.up_proj.weight', 'model.layers.0.post_attention_layernorm.weight', 'model.layers.0.self_attn.k_proj.weight', 'model.layers.0.self_attn.o_proj.weight', 'model.layers.0.self_attn.q_proj.weight', 'model.layers.0.self_attn.v_proj.weight', 'model.layers.1.input_layernorm.weight', 'model.layers.1.mlp.down_proj.weight', 'model.layers.1.mlp.gate_proj.weight', 'model.layers.1.mlp.up_proj.weight', 'model.layers.1.post_attention_layernorm.weight', 'model.layers.1.self_attn.k_proj.weight', 'model.layers.1.self_attn.o_proj.weight', 'model.layers.1.self_attn.q_proj.weight', 'model.layers.1.self_attn.v_proj.weight', 'model.layers.10.input_layernorm.weight', 'model.layers.10.mlp.down_proj.weight', 'model.layers.10.mlp.gate_proj.weight', 'model.layers.10.mlp.up_proj.weight', 'model.layers.10.post_attention_layernorm.weight', 'model.layers.10.self_attn.k_proj.weight', 'model.layers.10.self_attn.o_proj.weight', 'model.layers.10.self_attn.q_proj.weight', 'model.layers.10.self_attn.v_proj.weight', 'model.layers.11.input_layernorm.weight', 'model.layers.11.mlp.down_proj.weight', 'model.layers.11.mlp.gate_proj.weight', 'model.layers.11.mlp.up_proj.weight', 'model.layers.11.post_attention_layernorm.weight', 'model.layers.11.self_attn.k_proj.weight', 'model.layers.11.self_attn.o_proj.weight', 'model.layers.11.self_attn.q_proj.weight', 'model.layers.11.self_attn.v_proj.weight', 'model.layers.12.input_layernorm.weight', 'model.layers.12.mlp.down_proj.weight', 'model.layers.12.mlp.gate_proj.weight', 'model.layers.12.mlp.up_proj.weight', 'model.layers.12.post_attention_layernorm.weight', 'model.layers.12.self_attn.k_proj.weight', 'model.layers.12.self_attn.o_proj.weight', 'model.layers.12.self_attn.q_proj.weight', 'model.layers.12.self_attn.v_proj.weight', 'model.layers.13.input_layernorm.weight', 'model.layers.13.mlp.down_proj.weight', 'model.layers.13.mlp.gate_proj.weight', 'model.layers.13.mlp.up_proj.weight', 'model.layers.13.post_attention_layernorm.weight', 'model.layers.13.self_attn.k_proj.weight', 'model.layers.13.self_attn.o_proj.weight', 'model.layers.13.self_attn.q_proj.weight', 'model.layers.13.self_attn.v_proj.weight', 'model.layers.14.input_layernorm.weight', 'model.layers.14.mlp.down_proj.weight', 'model.layers.14.mlp.gate_proj.weight', 'model.layers.14.mlp.up_proj.weight', 'model.layers.14.post_attention_layernorm.weight', 'model.layers.14.self_attn.k_proj.weight', 'model.layers.14.self_attn.o_proj.weight', 'model.layers.14.self_attn.q_proj.weight', 'model.layers.14.self_attn.v_proj.weight', 'model.layers.15.input_layernorm.weight', 'model.layers.15.mlp.down_proj.weight', 'model.layers.15.mlp.gate_proj.weight', 'model.layers.15.mlp.up_proj.weight', 'model.layers.15.post_attention_layernorm.weight', 'model.layers.15.self_attn.k_proj.weight', 'model.layers.15.self_attn.o_proj.weight', 'model.layers.15.self_attn.q_proj.weight', 'model.layers.15.self_attn.v_proj.weight', 'model.layers.16.input_layernorm.weight', 'model.layers.16.mlp.down_proj.weight', 'model.layers.16.mlp.gate_proj.weight', 'model.layers.16.mlp.up_proj.weight', 'model.layers.16.post_attention_layernorm.weight', 'model.layers.16.self_attn.k_proj.weight', 'model.layers.16.self_attn.o_proj.weight', 'model.layers.16.self_attn.q_proj.weight', 'model.layers.16.self_attn.v_proj.weight', 'model.layers.17.input_layernorm.weight', 'model.layers.17.mlp.down_proj.weight', 'model.layers.17.mlp.gate_proj.weight', 'model.layers.17.mlp.up_proj.weight', 'model.layers.17.post_attention_layernorm.weight', 'model.layers.17.self_attn.k_proj.weight', 'model.layers.17.self_attn.o_proj.weight', 'model.layers.17.self_attn.q_proj.weight', 'model.layers.17.self_attn.v_proj.weight', 'model.layers.18.input_layernorm.weight', 'model.layers.18.mlp.down_proj.weight', 'model.layers.18.mlp.gate_proj.weight', 'model.layers.18.mlp.up_proj.weight', 'model.layers.18.post_attention_layernorm.weight', 'model.layers.18.self_attn.k_proj.weight', 'model.layers.18.self_attn.o_proj.weight', 'model.layers.18.self_attn.q_proj.weight', 'model.layers.18.self_attn.v_proj.weight', 'model.layers.19.input_layernorm.weight', 'model.layers.19.mlp.down_proj.weight', 'model.layers.19.mlp.gate_proj.weight', 'model.layers.19.mlp.up_proj.weight', 'model.layers.19.post_attention_layernorm.weight', 'model.layers.19.self_attn.k_proj.weight', 'model.layers.19.self_attn.o_proj.weight', 'model.layers.19.self_attn.q_proj.weight', 'model.layers.19.self_attn.v_proj.weight', 'model.layers.2.input_layernorm.weight', 'model.layers.2.mlp.down_proj.weight', 'model.layers.2.mlp.gate_proj.weight', 'model.layers.2.mlp.up_proj.weight', 'model.layers.2.post_attention_layernorm.weight', 'model.layers.2.self_attn.k_proj.weight', 'model.layers.2.self_attn.o_proj.weight', 'model.layers.2.self_attn.q_proj.weight', 'model.layers.2.self_attn.v_proj.weight', 'model.layers.20.input_layernorm.weight', 'model.layers.20.mlp.down_proj.weight', 'model.layers.20.mlp.gate_proj.weight', 'model.layers.20.mlp.up_proj.weight', 'model.layers.20.post_attention_layernorm.weight', 'model.layers.20.self_attn.k_proj.weight', 'model.layers.20.self_attn.o_proj.weight', 'model.layers.20.self_attn.q_proj.weight', 'model.layers.20.self_attn.v_proj.weight', 'model.layers.21.input_layernorm.weight', 'model.layers.21.mlp.down_proj.weight', 'model.layers.21.mlp.gate_proj.weight', 'model.layers.21.mlp.up_proj.weight', 'model.layers.21.post_attention_layernorm.weight', 'model.layers.21.self_attn.k_proj.weight', 'model.layers.21.self_attn.o_proj.weight', 'model.layers.21.self_attn.q_proj.weight', 'model.layers.21.self_attn.v_proj.weight', 'model.layers.22.input_layernorm.weight', 'model.layers.22.mlp.down_proj.weight', 'model.layers.22.mlp.gate_proj.weight', 'model.layers.22.mlp.up_proj.weight', 'model.layers.22.post_attention_layernorm.weight', 'model.layers.22.self_attn.k_proj.weight', 'model.layers.22.self_attn.o_proj.weight', 'model.layers.22.self_attn.q_proj.weight', 'model.layers.22.self_attn.v_proj.weight', 'model.layers.23.input_layernorm.weight', 'model.layers.23.mlp.down_proj.weight', 'model.layers.23.mlp.gate_proj.weight', 'model.layers.23.mlp.up_proj.weight', 'model.layers.23.post_attention_layernorm.weight', 'model.layers.23.self_attn.k_proj.weight', 'model.layers.23.self_attn.o_proj.weight', 'model.layers.23.self_attn.q_proj.weight', 'model.layers.23.self_attn.v_proj.weight', 'model.layers.24.input_layernorm.weight', 'model.layers.24.mlp.down_proj.weight', 'model.layers.24.mlp.gate_proj.weight', 'model.layers.24.mlp.up_proj.weight', 'model.layers.24.post_attention_layernorm.weight', 'model.layers.24.self_attn.k_proj.weight', 'model.layers.24.self_attn.o_proj.weight', 'model.layers.24.self_attn.q_proj.weight', 'model.layers.24.self_attn.v_proj.weight', 'model.layers.25.input_layernorm.weight', 'model.layers.25.mlp.down_proj.weight', 'model.layers.25.mlp.gate_proj.weight', 'model.layers.25.mlp.up_proj.weight', 'model.layers.25.post_attention_layernorm.weight', 'model.layers.25.self_attn.k_proj.weight', 'model.layers.25.self_attn.o_proj.weight', 'model.layers.25.self_attn.q_proj.weight', 'model.layers.25.self_attn.v_proj.weight', 'model.layers.26.input_layernorm.weight', 'model.layers.26.mlp.down_proj.weight', 'model.layers.26.mlp.gate_proj.weight', 'model.layers.26.mlp.up_proj.weight', 'model.layers.26.post_attention_layernorm.weight', 'model.layers.26.self_attn.k_proj.weight', 'model.layers.26.self_attn.o_proj.weight', 'model.layers.26.self_attn.q_proj.weight', 'model.layers.26.self_attn.v_proj.weight', 'model.layers.27.input_layernorm.weight', 'model.layers.27.mlp.down_proj.weight', 'model.layers.27.mlp.gate_proj.weight', 'model.layers.27.mlp.up_proj.weight', 'model.layers.27.post_attention_layernorm.weight', 'model.layers.27.self_attn.k_proj.weight', 'model.layers.27.self_attn.o_proj.weight', 'model.layers.27.self_attn.q_proj.weight', 'model.layers.27.self_attn.v_proj.weight', 'model.layers.3.input_layernorm.weight', 'model.layers.3.mlp.down_proj.weight', 'model.layers.3.mlp.gate_proj.weight', 'model.layers.3.mlp.up_proj.weight', 'model.layers.3.post_attention_layernorm.weight', 'model.layers.3.self_attn.k_proj.weight', 'model.layers.3.self_attn.o_proj.weight', 'model.layers.3.self_attn.q_proj.weight', 'model.layers.3.self_attn.v_proj.weight', 'model.layers.4.input_layernorm.weight', 'model.layers.4.mlp.down_proj.weight', 'model.layers.4.mlp.gate_proj.weight', 'model.layers.4.mlp.up_proj.weight', 'model.layers.4.post_attention_layernorm.weight', 'model.layers.4.self_attn.k_proj.weight', 'model.layers.4.self_attn.o_proj.weight', 'model.layers.4.self_attn.q_proj.weight', 'model.layers.4.self_attn.v_proj.weight', 'model.layers.5.input_layernorm.weight', 'model.layers.5.mlp.down_proj.weight', 'model.layers.5.mlp.gate_proj.weight', 'model.layers.5.mlp.up_proj.weight', 'model.layers.5.post_attention_layernorm.weight', 'model.layers.5.self_attn.k_proj.weight', 'model.layers.5.self_attn.o_proj.weight', 'model.layers.5.self_attn.q_proj.weight', 'model.layers.5.self_attn.v_proj.weight', 'model.layers.6.input_layernorm.weight', 'model.layers.6.mlp.down_proj.weight', 'model.layers.6.mlp.gate_proj.weight', 'model.layers.6.mlp.up_proj.weight', 'model.layers.6.post_attention_layernorm.weight', 'model.layers.6.self_attn.k_proj.weight', 'model.layers.6.self_attn.o_proj.weight', 'model.layers.6.self_attn.q_proj.weight', 'model.layers.6.self_attn.v_proj.weight', 'model.layers.7.input_layernorm.weight', 'model.layers.7.mlp.down_proj.weight', 'model.layers.7.mlp.gate_proj.weight', 'model.layers.7.mlp.up_proj.weight', 'model.layers.7.post_attention_layernorm.weight', 'model.layers.7.self_attn.k_proj.weight', 'model.layers.7.self_attn.o_proj.weight', 'model.layers.7.self_attn.q_proj.weight', 'model.layers.7.self_attn.v_proj.weight', 'model.layers.8.input_layernorm.weight', 'model.layers.8.mlp.down_proj.weight', 'model.layers.8.mlp.gate_proj.weight', 'model.layers.8.mlp.up_proj.weight', 'model.layers.8.post_attention_layernorm.weight', 'model.layers.8.self_attn.k_proj.weight', 'model.layers.8.self_attn.o_proj.weight', 'model.layers.8.self_attn.q_proj.weight', 'model.layers.8.self_attn.v_proj.weight', 'model.layers.9.input_layernorm.weight', 'model.layers.9.mlp.down_proj.weight', 'model.layers.9.mlp.gate_proj.weight', 'model.layers.9.mlp.up_proj.weight', 'model.layers.9.post_attention_layernorm.weight', 'model.layers.9.self_attn.k_proj.weight', 'model.layers.9.self_attn.o_proj.weight', 'model.layers.9.self_attn.q_proj.weight', 'model.layers.9.self_attn.v_proj.weight', 'model.norm.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
最新发布
Google Maps近期更新了图层叠加功能，用户可以开启额外的信息层，如Panoramio和Wikipedia，以此来查看地图上的图片和百科信息。这一功能让用户能够通过点击图标来获取特定地点的照片或百科介绍。
扫一扫
2184
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
