null function or function signature mismatch at wllama.wasm
Closed this issue · 5 comments
flatsiedatsie commented
I'm catching a lot of errors like this:
While attempting to load:
https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/resolve/main/h2o-danube2-1.8b-chat-Q5_0.gguf
..with a 8192 context.
I'm probably doing something wrong. From what I could find online, perhaps it has something to do with improper callbacks?
Full log:
Loading "wllama.wasm" from "https://localhostje.dd/wasm4/esm/multi-thread/wllama.wasm"
32worker.ts:250 Loading "wllama.worker.mjs" from "https://localhostje.dd/wasm4/esm/multi-thread/wllama.worker.mjs"
worker.ts:251 AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 1 | BLAS = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 |
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: loaded meta data with 27 key-value pairs and 219 tensors from /models/model.gguf (version GGUF V3 (latest))
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 0: general.architecture str = llama
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 1: general.name str = h2o-danube2-1.8b-chat
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 2: llama.block_count u32 = 24
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 3: llama.context_length u32 = 8192
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 4: llama.embedding_length u32 = 2560
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 6912
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 10000.000000
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 10: general.file_type u32 = 8
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 11: llama.vocab_size u32 = 32000
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 80
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 13: tokenizer.ggml.model str = llama
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 15: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 1
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 2
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 19: tokenizer.ggml.unknown_token_id u32 = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 20: tokenizer.ggml.seperator_token_id u32 = 2
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 22: tokenizer.ggml.cls_token_id u32 = 2
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 24: tokenizer.ggml.add_eos_token bool = false
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 25: tokenizer.chat_template str = {% for message in messages %}{% if me...
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - kv 26: general.quantization_version u32 = 2
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - type f32: 49 tensors
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - type q5_0: 169 tensors
onRecvMsg @ worker.ts:251
worker.ts:251 llama_model_loader: - type q6_K: 1 tensors
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_vocab: special tokens definition check successful ( 259/32000 ).
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: format = GGUF V3 (latest)
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: arch = llama
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: vocab type = SPM
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_vocab = 32000
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_merges = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_ctx_train = 8192
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_embd = 2560
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_head = 32
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_head_kv = 8
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_layer = 24
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_rot = 80
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_embd_head_k = 80
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_embd_head_v = 80
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_gqa = 4
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_embd_k_gqa = 640
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_embd_v_gqa = 640
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: f_norm_eps = 0.0e+00
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: f_norm_rms_eps = 1.0e-05
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: f_clamp_kqv = 0.0e+00
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: f_max_alibi_bias = 0.0e+00
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: f_logit_scale = 0.0e+00
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_ff = 6912
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_expert = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_expert_used = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: causal attn = 1
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: pooling type = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: rope type = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: rope scaling = linear
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: freq_base_train = 10000.0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: freq_scale_train = 1
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: n_yarn_orig_ctx = 8192
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: rope_finetuned = unknown
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: ssm_d_conv = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: ssm_d_inner = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: ssm_d_state = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: ssm_dt_rank = 0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: model type = ?B
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: model ftype = Q5_0
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: model params = 1.83 B
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: model size = 1.18 GiB (5.55 BPW)
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: general.name = h2o-danube2-1.8b-chat
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: BOS token = 1 '<s>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: EOS token = 2 '</s>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: UNK token = 0 '<unk>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: SEP token = 2 '</s>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: PAD token = 0 '<unk>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: CLS token = 2 '</s>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_print_meta: LF token = 13 '<0x0A>'
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_tensors: ggml ctx size = 0.09 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 llm_load_tensors: CPU buffer size = 1211.40 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 ............................................................................................warning: munmap failed: Invalid argument
onRecvMsg @ worker.ts:251
worker.ts:251 .
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: n_ctx = 8192
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: n_batch = 2048
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: n_ubatch = 512
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: freq_base = 10000.0
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: freq_scale = 1
onRecvMsg @ worker.ts:251
worker.ts:251 llama_kv_cache_init: CPU KV buffer size = 480.00 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: KV self size = 480.00 MiB, K (f16): 240.00 MiB, V (f16): 240.00 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: CPU output buffer size = 0.12 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: CPU compute buffer size = 548.01 MiB
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: graph nodes = 774
onRecvMsg @ worker.ts:251
worker.ts:251 llama_new_context_with_model: graph splits = 1
onRecvMsg @ worker.ts:251
llama_cpp.js:774 on
ngxson commented
Seems like cpp code throws an exception, but it's unable to display the exception correctly. I'll have a look in the next days when I have more time.
ngxson commented
Also have you tried with other parameters? For example lower context length or try with multi / single thread build
flatsiedatsie commented
Also have you tried with other parameters? For example lower context length or try with multi / single thread build
I have literally tried both those thing :-)
Singular, spaced out inference works fine. It believe it has something to do with running tasks one after the other, in quick succession (summarizing a document in mutiple chunks). Shortening context also helped, but for summarization defeats the point a bit.
There are more things I can try on this end. I'm trying to space tasks out more.
oh it just crashed again, darn.
// The Brave tab had grown to 16Gb, on a 1Gb model.
// I think my code is restarting a bit too eagerly on a crash with that one.
flatsiedatsie commented
I think the issue is in my code.
flatsiedatsie commented
I've done some more testing and found the issue. As predicted, it was in my code.
I was setting the model's context (n_ctx) size only, as that was the only variable of that nature that needed to be set in llama_cpp_wasm. But with Wllama, which offers much more low level control, the n_seq_max and n_batch values also needed to be set explicitly. Setting all three to the same value (8192 in this case) solved the issue.