abetlen
How to use this model?
llama_model_loader: loaded meta data with 32 key-value pairs and 219 tensors from /data/huggingface/hub/models--city96--t5-v1_1-xxl-encoder-gguf/snapshots/005a6ea51a7d0b84d677b3e633bb52a8c85a83d9/./t5-v1_1-xxl-encoder-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 = t5encoder llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = T5 V1_1 Xxl llama_model_loader: - kv 3: general.organization str = Google llama_model_loader: - kv 4: general.finetune str = encoder-hf llama_model_loader: - kv 5: general.basename str = t5-v1_1 llama_model_loader: - kv 6: general.size_label str = xxl llama_model_loader: - kv 7: t5encoder.context_length u32 = 512 llama_model_loader: - kv 8: t5encoder.embedding_length u32 = 4096 llama_model_loader: - kv 9: t5encoder.feed_forward_length u32 = 10240 llama_model_loader: - kv 10: t5encoder.block_count u32 = 24 llama_model_loader: - kv 11: t5encoder.attention.head_count u32 = 64 llama_model_loader: - kv 12: t5encoder.attention.key_length u32 = 64 llama_model_loader: - kv 13: t5encoder.attention.value_length u32 = 64 llama_model_loader: - kv 14: t5encoder.attention.layer_norm_epsilon f32 = 0.000001 llama_model_loader: - kv 15: t5encoder.attention.relative_buckets_count u32 = 32 llama_model_loader: - kv 16: t5encoder.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 17: general.file_type u32 = 7 llama_model_loader: - kv 18: tokenizer.ggml.model str = t5 llama_model_loader: - kv 19: tokenizer.ggml.pre str = default llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,32128] = ["", "", "", "▁", "X"... llama_model_loader: - kv 21: tokenizer.ggml.scores arr[f32,32128] = [0.000000, 0.000000, 0.000000, -2.012... llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,32128] = [3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 23: tokenizer.ggml.add_space_prefix bool = true llama_model_loader: - kv 24: tokenizer.ggml.remove_extra_whitespaces bool = true llama_model_loader: - kv 25: tokenizer.ggml.precompiled_charsmap arr[u8,237539] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,... llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 27: tokenizer.ggml.unknown_token_id u32 = 2 llama_model_loader: - kv 28: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 30: tokenizer.ggml.add_eos_token bool = true llama_model_loader: - kv 31: general.quantization_version u32 = 2 llama_model_loader: - type f32: 50 tensors llama_model_loader: - type q8_0: 169 tensors llm_load_vocab: special tokens cache size = 3 llm_load_vocab: token to piece cache size = 0.2111 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = t5encoder llm_load_print_meta: vocab type = UGM llm_load_print_meta: n_vocab = 32128 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 512 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 24 llm_load_print_meta: n_head = 64 llm_load_print_meta: n_head_kv = 64 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 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 = 4096 llm_load_print_meta: n_embd_v_gqa = 4096 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 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 = 10240 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 = -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_ctx_orig_yarn = 512 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: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 4.76 B llm_load_print_meta: model size = 4.71 GiB (8.50 BPW) llm_load_print_meta: general.name = T5 V1_1 Xxl llm_load_print_meta: EOS token = 1 '' llm_load_print_meta: UNK token = 2 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 3 '▁' llm_load_print_meta: max token length = 20 llm_load_tensors: ggml ctx size = 0.10 MiB llm_load_tensors: CPU buffer size = 4826.12 MiB ................................................................................................. llama_new_context_with_model: n_ctx = 512 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 10000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CPU KV buffer size = 192.00 MiB llama_new_context_with_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB llama_new_context_with_model: CPU output buffer size = 0.12 MiB llama_new_context_with_model: CPU compute buffer size = 234.00 MiB llama_new_context_with_model: graph nodes = 845 llama_new_context_with_model: graph splits = 1 AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | Model metadata: {'tokenizer.ggml.eos_token_id': '1', 'general.quantization_version': '2', 'tokenizer.ggml.model': 't5', 'tokenizer.ggml.add_bos_token': 'false', 'tokenizer.ggml.remove_extra_whitespaces': 'true', 't5encoder.attention.layer_norm_rms_epsilon': '0.000001', 't5encoder.attention.relative_buckets_count': '32', 't5encoder.attention.layer_norm_epsilon': '0.000001', 'tokenizer.ggml.unknown_token_id': '2', 't5encoder.attention.value_length': '64', 'general.architecture': 't5encoder', 'general.file_type': '7', 't5encoder.context_length': '512', 't5encoder.feed_forward_length': '10240', 'tokenizer.ggml.padding_token_id': '0', 'general.basename': 't5-v1_1', 'tokenizer.ggml.pre': 'default', 'general.name': 'T5 V1_1 Xxl', 'general.finetune': 'encoder-hf', 't5encoder.attention.key_length': '64', 'general.type': 'model', 't5encoder.attention.head_count': '64', 'general.size_label': 'xxl', 'general.organization': 'Google', 't5encoder.embedding_length': '4096', 'tokenizer.ggml.add_eos_token': 'true', 'tokenizer.ggml.add_space_prefix': 'true', 't5encoder.block_count': '24'} Using fallback chat format: llama-2 /tmp/pip-install-rx431hta/llama-cpp-python_78f9dcf2ce95424dbc2c1f7ebd107737/vendor/llama.cpp/src/llama.cpp:13908: GGML_ASSERT(lctx.is_encoding) failed /usr/local/lib/python3.10/dist-packages/llama_cpp/lib/libggml.so(+0x1015b)[0x7f42c791a15b] /usr/local/lib/python3.10/dist-packages/llama_cpp/lib/libggml.so(ggml_abort+0x15e)[0x7f42c791bd2e] /usr/local/lib/python3.10/dist-packages/llama_cpp/lib/libllama.so(_ZN17llm_build_context16build_t5_encoderEv+0x11a0)[0x7f42c7b5ef90] /usr/local/lib/python3.10/dist-packages/llama_cpp/lib/libllama.so(+0x80d92)[0x7f42c7ad7d92] /usr/local/lib/python3.10/dist-packages/llama_cpp/lib/libllama.so(llama_decode+0x582)[0x7f42c7b35972] /lib/x86_64-linux-gnu/libffi.so.8(+0x7e2e)[0x7f42c7e45e2e] /lib/x86_64-linux-gnu/libffi.so.8(+0x4493)[0x7f42c7e42493] /usr/lib/python3.10/lib-dynload/_ctypes.cpython-310-x86_64-linux-gnu.so(+0xa3e9)[0x7f42c7e603e9] /usr/lib/python3.10/lib-dynload/_ctypes.cpython-310-x86_64-linux-gnu.so(+0x13302)[0x7f42c7e69302] python3(_PyObject_MakeTpCall+0x25b)[0x55a5b37e152b] python3(_PyEval_EvalFrameDefault+0x6f0b)[0x55a5b37da16b] python3(_PyFunction_Vectorcall+0x7c)[0x55a5b37eb6ac] python3(_PyEval_EvalFrameDefault+0x8cb)[0x55a5b37d3b2b] python3(_PyFunction_Vectorcall+0x7c)[0x55a5b37eb6ac] python3(_PyEval_EvalFrameDefault+0x8cb)[0x55a5b37d3b2b] python3(+0x1785a2)[0x55a5b38085a2] python3(_PyEval_EvalFrameDefault+0xac4)[0x55a5b37d3d24] python3(+0x201a15)[0x55a5b3891a15] python3(+0x15b909)[0x55a5b37eb909] python3(_PyEval_EvalFrameDefault+0x6d5)[0x55a5b37d3935] python3(+0x169251)[0x55a5b37f9251] python3(PyObject_Call+0x122)[0x55a5b37f9f02] python3(_PyEval_EvalFrameDefault+0x2a49)[0x55a5b37d5ca9] python3(_PyFunction_Vectorcall+0x7c)[0x55a5b37eb6ac] python3(PyObject_Call+0x122)[0x55a5b37f9f02] python3(_PyEval_EvalFrameDefault+0x2a49)[0x55a5b37d5ca9] python3(+0x169251)[0x55a5b37f9251] python3(_PyEval_EvalFrameDefault+0x19b6)[0x55a5b37d4c16] python3(+0x140096)[0x55a5b37d0096] python3(PyEval_EvalCode+0x86)[0x55a5b38c5f66] python3(+0x260e98)[0x55a5b38f0e98] python3(+0x25a79b)[0x55a5b38ea79b] python3(+0x260be5)[0x55a5b38f0be5] python3(_PyRun_SimpleFileObject+0x1a8)[0x55a5b38f00c8] python3(_PyRun_AnyFileObject+0x43)[0x55a5b38efd13] python3(Py_RunMain+0x2be)[0x55a5b38e270e] python3(Py_BytesMain+0x2d)[0x55a5b38b8dfd] /lib/x86_64-linux-gnu/libc.so.6(+0x29d90)[0x7f42c8512d90] /lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x80)[0x7f42c8512e40] python3(_start+0x25)[0x55a5b38b8cf5] Aborted (core dumped)
Has anyone else had this problem?
from llama_cpp import Llama llm = Llama( model_path="/data/app/comfyui/ComfyUI/models/clip/t5/t5-v1_1-xxl-encoder-Q8_0.gguf", chat_format="llama-2" ) llm.create_chat_completion( messages = [ {"role": "system", "content": "You are an assistant who perfectly describes images."}, { "role": "user", "content": "Describe this image in detail please." } ] )
