Open
Description
Name and Version
version: 5286 (b57b9ed)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
Operating systems
Other? (Please let us know in description)
GGML backends
CPU
Hardware
AMD Ryzen 5 5600 6-Core Processor 3.50 GHz.
Models
Problem description & steps to reproduce
when I run build/bin/llama-cli -hf Sparkoo/KateAI:Q5_K_M -p "Once upon a time,", It fails. I don't know if it's the script, my custom llama.cpp, or something else. (Don't tell me to redownload it, I tried many times!!). My OS is WSL 2 (Ubuntu 22.04). My custom llama.cpp: llama.cpp-1. I'm pretty sure I put in all of the weights and biases. If you know why this could be happening please respond to this issue!
Relevant log output
curl_perform_with_retry: HEAD https://huggingface.co/Sparkoo/KateAI/resolve/main/KateAI.Q5_K_M.gguf (attempt 1 of 1)...
common_download_file_single: using cached file: /home/ai/.cache/llama.cpp/Sparkoo_KateAI_KateAI.Q5_K_M.gguf
build: 5286 (b57b9ed3) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 22 key-value pairs and 132 tensors from /home/ai/.cache/llama.cpp/Sparkoo_KateAI_KateAI.Q5_K_M.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 = kateai
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = Kateai
llama_model_loader: - kv 3: general.size_label str = 134M
llama_model_loader: - kv 4: general.tags arr[str,1] = ["text-generation"]
llama_model_loader: - kv 5: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 6: kateai.context_length u32 = 512
llama_model_loader: - kv 7: kateai.embedding_length u32 = 768
llama_model_loader: - kv 8: kateai.block_count u32 = 8
llama_model_loader: - kv 9: kateai.attention.head_count u32 = 8
llama_model_loader: - kv 10: kateai.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 11: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 12: tokenizer.ggml.pre str = gpt-2
llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,50257] = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 14: tokenizer.ggml.token_type arr[i32,50257] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 15: tokenizer.ggml.merges arr[str,50000] = ["Ġ t", "Ġ a", "h e", "i n", "r e",...
llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 50256
llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 50256
llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 50256
llama_model_loader: - kv 19: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 20: general.quantization_version u32 = 2
llama_model_loader: - kv 21: general.file_type u32 = 17
llama_model_loader: - type f32: 82 tensors
llama_model_loader: - type q5_K: 41 tensors
llama_model_loader: - type q6_K: 9 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q5_K - Medium
print_info: file size = 96.12 MiB (6.00 BPW)
load: special tokens cache size = 1
load: token to piece cache size = 0.3060 MB
print_info: arch = kateai
print_info: vocab_only = 0
print_info: n_ctx_train = 512
print_info: n_embd = 768
print_info: n_layer = 8
print_info: n_head = 8
print_info: n_head_kv = 8
print_info: n_rot = 96
print_info: n_swa = 0
print_info: n_swa_pattern = 1
print_info: n_embd_head_k = 96
print_info: n_embd_head_v = 96
print_info: n_gqa = 1
print_info: n_embd_k_gqa = 768
print_info: n_embd_v_gqa = 768
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-06
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: f_attn_scale = 0.0e+00
print_info: n_ff = 0
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = -1
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 512
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 137M
print_info: model params = 134.34 M
print_info: general.name = Kateai
print_info: vocab type = BPE
print_info: n_vocab = 50257
print_info: n_merges = 50000
print_info: BOS token = 50256 '<|endoftext|>'
print_info: EOS token = 50256 '<|endoftext|>'
print_info: EOT token = 50256 '<|endoftext|>'
print_info: PAD token = 50256 '<|endoftext|>'
print_info: LF token = 198 'Ċ'
print_info: EOG token = 50256 '<|endoftext|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
llama_model_load: error loading model: missing tensor '__missing__'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/home/ai/.cache/llama.cpp/Sparkoo_KateAI_KateAI.Q5_K_M.gguf'
main: error: unable to load model