QuantFactory/CausalLM-35b-beta-long-GGUF · check_tensor_dims: tensor 'token_embd.weight' has wrong shape; expected 8192, 255029, got 8192, 256000, 1, 1

The llama-cpp-python is unable to run, reporting an error: check_tensor_dims: the tensor 'token_embd.weight' has an incorrect shape; expected shape is 8192, 255029, but received 8192, 256000, 1, 1.

from llama_cpp import Llama

llm = Llama(
    model_path=r"J:\AI\CausalLM-35b-beta-long-GGUF\CausalLM-35b-beta-long.Q2_K.gguf",
    chat_format="llama-2"
)
output = llm(
      "Q: 来一段西厢记风格的情感小说，100字，要露骨，不要套路。 A: ", # Prompt
      max_tokens=None, # Generate up to 32 tokens, set to None to generate up to the end of the context window
      stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
      echo=True # Echo the prompt back in the output
) # Generate a completion, can also call create_completion
print(output)

Report

C:\ProgramData\anaconda3\envs\python311\python.exe C:\Users\Administrator\Personal_scripts\Python\PythonScripts\PythonScripts\test\temp.py 
llama_model_loader: loaded meta data with 25 key-value pairs and 322 tensors from J:\AI\CausalLM-35b-beta-long-GGUF\CausalLM-35b-beta-long.Q2_K.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = models
llama_model_loader: - kv   2:                           llama.vocab_size u32              = 255029
llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
llama_model_loader: - kv   4:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv   5:                          llama.block_count u32              = 40
llama_model_loader: - kv   6:                  llama.feed_forward_length u32              = 22528
llama_model_loader: - kv   7:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   8:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv   9:              llama.attention.head_count_kv u32              = 64
llama_model_loader: - kv  10:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  11:                       llama.rope.freq_base f32              = 8000000.000000
llama_model_loader: - kv  12:                          general.file_type u32              = 10
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,255029]  = ["<PAD>", "<UNK>", "<CLS>", "<SEP>", ...
llama_model_loader: - kv  15:                      tokenizer.ggml.scores arr[f32,255029]  = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,255029]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,253333]  = ["Ġ Ġ", "Ġ t", "e r", "i n", "Ġ a...
llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 5
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 6
llama_model_loader: - kv  20:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  21:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  22:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  23:                    tokenizer.chat_template str              = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv  24:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   41 tensors
llama_model_loader: - type q2_K:  160 tensors
llama_model_loader: - type q3_K:  120 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: missing pre-tokenizer type, using: 'default'
llm_load_vocab:                                             
llm_load_vocab: ************************************        
llm_load_vocab: GENERATION QUALITY WILL BE DEGRADED!        
llm_load_vocab: CONSIDER REGENERATING THE MODEL             
llm_load_vocab: ************************************        
llm_load_vocab:                                             
llm_load_vocab: special tokens cache size = 29
llm_load_vocab: token to piece cache size = 1.8426 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 255029
llm_load_print_meta: n_merges         = 253333
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 8192
llm_load_print_meta: n_embd           = 8192
llm_load_print_meta: n_layer          = 40
llm_load_print_meta: n_head           = 64
llm_load_print_meta: n_head_kv        = 64
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 8192
llm_load_print_meta: n_embd_v_gqa     = 8192
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 22528
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 8000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 8192
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: model type       = 13B
llm_load_print_meta: model ftype      = Q2_K - Medium
llm_load_print_meta: model params     = 34.98 B
llm_load_print_meta: model size       = 12.86 GiB (3.16 BPW) 
llm_load_print_meta: general.name     = models
llm_load_print_meta: BOS token        = 5 '<s>'
llm_load_print_meta: EOS token        = 6 '</s>'
llm_load_print_meta: PAD token        = 0 '<PAD>'
llm_load_print_meta: LF token         = 136 'Ä'
llm_load_print_meta: EOT token        = 255001 '<|im_end|>'
llm_load_print_meta: max token length = 1024
llm_load_tensors: ggml ctx size =    0.16 MiB
llama_model_load: error loading model: check_tensor_dims: tensor 'token_embd.weight' has wrong shape; expected  8192, 255029, got  8192, 256000,     1,     1
llama_load_model_from_file: failed to load model
Traceback (most recent call last):
  File "C:\Users\Administrator\Personal_scripts\Python\PythonScripts\PythonScripts\test\temp.py", line 6, in <module>
    llm = Llama(
          ^^^^^^
  File "C:\ProgramData\anaconda3\envs\python311\Lib\site-packages\llama_cpp\llama.py", line 358, in __init__
    self._model = self._stack.enter_context(contextlib.closing(_LlamaModel(
                                                               ^^^^^^^^^^^^
  File "C:\ProgramData\anaconda3\envs\python311\Lib\site-packages\llama_cpp\_internals.py", line 54, in __init__
    raise ValueError(f"Failed to load model from file: {path_model}")
ValueError: Failed to load model from file: J:\AI\CausalLM-35b-beta-long-GGUF\CausalLM-35b-beta-long.Q2_K.gguf