s3nh

/

MiniCPM-2B-dpo-fp32-GGUF

like 8

good job guy! but some error loading with llama.cpp:

root@wk:/home/lotus# cllama --color -t 32 -ins --log-append -m /data/ai/minicpm-2b-dpo-fp32.Q8_0.gguf
Log start
main: build = 0 (unknown)
main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: seed = 1706930503
llama_model_loader: loaded meta data with 22 key-value pairs and 362 tensors from /data/ai/minicpm-2b-dpo-fp32.Q8_0.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 = MiniCPM-2B-dpo-fp32
llama_model_loader: - kv 2: llama.context_length u32 = 2048
llama_model_loader: - kv 3: llama.embedding_length u32 = 2304
llama_model_loader: - kv 4: llama.block_count u32 = 40
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 5760
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 64
llama_model_loader: - kv 7: llama.attention.head_count u32 = 36
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 36
llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 10: general.file_type u32 = 7
llama_model_loader: - kv 11: tokenizer.ggml.model str = llama
llama_model_loader: - kv 12: tokenizer.ggml.tokens arr[str,122753] = ["", "", "", "", "<C...
llama_model_loader: - kv 13: tokenizer.ggml.scores arr[f32,122753] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,122753] = [2, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 16: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 17: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 18: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 19: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 20: tokenizer.chat_template str = {% for message in messages %}{% if me...
llama_model_loader: - kv 21: general.quantization_version u32 = 2
llama_model_loader: - type f32: 81 tensors
llama_model_loader: - type q8_0: 281 tensors
llm_load_vocab: mismatch in special tokens definition ( 3528/122753 vs 259/122753 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 122753
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 2048
llm_load_print_meta: n_embd = 2304
llm_load_print_meta: n_head = 36
llm_load_print_meta: n_head_kv = 36
llm_load_print_meta: n_layer = 40
llm_load_print_meta: n_rot = 64
llm_load_print_meta: n_embd_head_k = 64
llm_load_print_meta: n_embd_head_v = 64
llm_load_print_meta: n_gqa = 1
llm_load_print_meta: n_embd_k_gqa = 2304
llm_load_print_meta: n_embd_v_gqa = 2304
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: n_ff = 5760
llm_load_print_meta: n_expert = 0
llm_load_print_meta: n_expert_used = 0
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 2048
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 13B
llm_load_print_meta: model ftype = Q8_0
llm_load_print_meta: model params = 2.72 B
llm_load_print_meta: model size = 2.70 GiB (8.50 BPW)
llm_load_print_meta: general.name = MiniCPM-2B-dpo-fp32
llm_load_print_meta: BOS token = 1 ''
llm_load_print_meta: EOS token = 2 ''
llm_load_print_meta: UNK token = 0 ''
llm_load_print_meta: LF token = 1099 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.14 MiB
llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/data/ai/minicpm-2b-dpo-fp32.Q8_0.gguf'
main: error: unable to load model