Not working with llama-cpp-python

#1
by hassan404 - opened

Following the instructions given here https://llama-cpp-python.readthedocs.io/en/latest/server/#code-completion

Command used: python3 -m llama_cpp.server --model replit-code-v1_5-3b.f16.gguf --n_ctx 16192

Console output

llama_model_loader: loaded meta data with 17 key-value pairs and 195 tensors from replit-code-v1_5-3b.f16.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              = mpt
llama_model_loader: - kv   1:                               general.name str              = replit-code-v1_5-3b
llama_model_loader: - kv   2:                         mpt.context_length u32              = 4096
llama_model_loader: - kv   3:                       mpt.embedding_length u32              = 3072
llama_model_loader: - kv   4:                            mpt.block_count u32              = 32
llama_model_loader: - kv   5:                    mpt.feed_forward_length u32              = 12288
llama_model_loader: - kv   6:                   mpt.attention.head_count u32              = 24
llama_model_loader: - kv   7:                mpt.attention.head_count_kv u32              = 8
llama_model_loader: - kv   8:           mpt.attention.layer_norm_epsilon f32              = 0.000010
llama_model_loader: - kv   9:               mpt.attention.max_alibi_bias f32              = 8.000000
llama_model_loader: - kv  10:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  11:                      tokenizer.ggml.tokens arr[str,32768]   = ["<|endoftext|>", "<|padding|>", "<fi...
llama_model_loader: - kv  12:                  tokenizer.ggml.token_type arr[i32,32768]   = [3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, ...
llama_model_loader: - kv  13:                      tokenizer.ggml.merges arr[str,32494]   = ["Ġ Ġ", "ĠĠ ĠĠ", "ĠĠĠĠ ĠĠ...
llama_model_loader: - kv  14:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  15:                tokenizer.ggml.eos_token_id u32              = 0
llama_model_loader: - kv  16:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type  f16:  130 tensors
llm_load_vocab: special tokens definition check successful ( 18/32768 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = mpt
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 32768
llm_load_print_meta: n_merges         = 32494
llm_load_print_meta: n_ctx_train      = 4096
llm_load_print_meta: n_embd           = 3072
llm_load_print_meta: n_head           = 24
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 3
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 1.0e-05
llm_load_print_meta: f_norm_rms_eps   = 0.0e+00
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 8.0e+00
llm_load_print_meta: n_ff             = 12288
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = -1
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  = 4096
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = F16 (guessed)
llm_load_print_meta: model params     = 3.42 B
llm_load_print_meta: model size       = 6.38 GiB (16.00 BPW) 
llm_load_print_meta: general.name     = replit-code-v1_5-3b
llm_load_print_meta: BOS token        = 0 '<|endoftext|>'
llm_load_print_meta: EOS token        = 0 '<|endoftext|>'
llm_load_print_meta: UNK token        = 0 '<|endoftext|>'
llm_load_print_meta: LF token         = 146 'Ä'
llm_load_tensors: ggml ctx size =    0.07 MiB
llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 195, got 194
llama_load_model_from_file: failed to load model

llama_cpp.server did not work with any model
with me

Sign up or log in to comment