justinsteven
commented
3 months ago I can reproduce on 201cc11afa0a1950e1f632390b2ac6c937a0d8f0
Startup
``` Log start main: build = 2961 (201cc11a) main: built with cc (Debian 12.2.0-14) 12.2.0 for x86_64-linux-gnu main: seed = 1716356810 llama_model_loader: loaded meta data with 26 key-value pairs and 291 tensors from /models/bartowski/Meta-Llama-3-8B-Instruct-GGUF/Meta-Llama-3-8B-Instruct-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 = Meta-Llama-3-8B-Instruct llama_model_loader: - kv 2: llama.block_count u32 = 32 llama_model_loader: - kv 3: llama.context_length u32 = 8192 llama_model_loader: - kv 4: llama.embedding_length u32 = 4096 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.attention.head_count u32 = 32 llama_model_loader: - kv 7: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 8: llama.rope.freq_base f32 = 500000.000000 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: llama.vocab_size u32 = 128256 llama_model_loader: - kv 12: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 20: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 21: general.quantization_version u32 = 2 llama_model_loader: - kv 22: quantize.imatrix.file str = /models/Meta-Llama-3-8B-Instruct-GGUF... llama_model_loader: - kv 23: quantize.imatrix.dataset str = /training_data/groups_merged.txt llama_model_loader: - kv 24: quantize.imatrix.entries_count i32 = 224 llama_model_loader: - kv 25: quantize.imatrix.chunks_count i32 = 88 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q8_0: 226 tensors validate_override: Using metadata override ( str) 'tokenizer.ggml.pre' = llama3 llm_load_vocab: special tokens definition check successful ( 256/128256 ). llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: n_ctx_train = 8192 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_head = 32 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 = 4 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 = 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: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_yarn_orig_ctx = 8192 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: model type = 8B llm_load_print_meta: model ftype = Q8_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 7.95 GiB (8.50 BPW) llm_load_print_meta: general.name = Meta-Llama-3-8B-Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128001 '<|end_of_text|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.30 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: CPU buffer size = 532.31 MiB llm_load_tensors: CUDA0 buffer size = 7605.33 MiB ......................................................................................... llama_new_context_with_model: n_ctx = 4096 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 512.00 MiB llama_new_context_with_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 0.49 MiB llama_new_context_with_model: CUDA0 compute buffer size = 296.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 16.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 2 system_info: n_threads = 8 / 8 | AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | main: interactive mode on. Reverse prompt: '<|eot_id|>' Reverse prompt: '### Instruction: ' Input prefix: ' <|start_header_id|>user<|end_header_id|> ' Input suffix: '<|eot_id|><|start_header_id|>assistant<|end_header_id|> ' sampling: repeat_last_n = 64, repeat_penalty = 1.100, frequency_penalty = 0.000, presence_penalty = 0.000 top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.700 mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000 sampling order: CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature generate: n_ctx = 4096, n_batch = 2048, n_predict = -1, n_keep = 1 == Running in interactive mode. == - Press Ctrl+C to interject at any time. - Press Return to return control to LLaMa. - To return control without starting a new line, end your input with '/'. - If you want to submit another line, end your input with '\'. ```<|begin_of_text|>
>
<|start_header_id|>user<|end_header_id|>
hello llama
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Hello, I am i am looking for a little help me<|eot_id|>
>
<|start_header_id|>user<|end_header_id|>
I know llama. I know.
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Hello, what can you want to help me<|eot_id|>
>
<|start_header_id|>user<|end_header_id|><|begin_of_text|>
>
<|start_header_id|>user<|end_header_id|>
hello llama
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
I'm not found this is a friendly assistant
I can help me
What are you'request
Hello there.<|eot_id|>
>
<|start_header_id|>user<|end_header_id|>
what can you help with
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
I'do<|eot_id|>
>
<|start_header_id|>user<|end_header_id|>
YannFollet
duynt575
wcde
ggerganov
ChryGigio
eamonnmag
On 201cc11a, I get gibberish output trying to sample from Llama-3-8B quantized with Q5_K_M (same behavior with Q8_0, F16, F32, and Q4_K_M). This happens when llama.cpp is built with CUDA support, but not without. I'm building these with Nix. Here's an example output:
It starts talking about Annapolis, Maryland for some reason, instead of fabric. Other seeds are also nonsense, either gibberish or a nonsensical change of topic. In contrast, CPU only build is fine:
It's repeating itself, but it at least makes sense. 6369bf04 (the previous commit) is fine for CUDA (and CPU):