metadata
library_name: transformers
license: other
license_name: exaone
license_link: LICENSE
language:
- en
- ko
tags:
- lg-ai
- exaone
EXAONE-3.0-8B-it
[!WARNING]
https://github.com/ggerganov/llama.cpp/wiki/Templates-supported-by-llama_chat_apply_template
chat template μ μ© μλ¨
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="Bingsu/exaone-3.0-7.8b-it",
filename="exaone-3.0-7.8B-it-Q8_0.gguf"
)
llama_model_loader: loaded meta data with 34 key-value pairs and 291 tensors from /root/.cache/huggingface/hub/models--Bingsu--exaone-3.0-7.8b-it/snapshots/c7b9c43a7d1db6509b40e9b18f10ae0554b3d4cb/./exaone-3.0-7.8B-it-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.type str = model
llama_model_loader: - kv 2: general.name str = Exaone 3.0 7.8b It
llama_model_loader: - kv 3: general.finetune str = it
llama_model_loader: - kv 4: general.basename str = exaone-3.0
llama_model_loader: - kv 5: general.size_label str = 7.8B
llama_model_loader: - kv 6: general.license str = other
llama_model_loader: - kv 7: general.license.name str = exaone
llama_model_loader: - kv 8: general.license.link str = LICENSE
llama_model_loader: - kv 9: general.tags arr[str,2] = ["lg-ai", "exaone"]
llama_model_loader: - kv 10: general.languages arr[str,2] = ["en", "ko"]
llama_model_loader: - kv 11: llama.block_count u32 = 32
llama_model_loader: - kv 12: llama.context_length u32 = 4096
llama_model_loader: - kv 13: llama.embedding_length u32 = 4096
llama_model_loader: - kv 14: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 15: llama.attention.head_count u32 = 32
llama_model_loader: - kv 16: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 17: llama.rope.freq_base f32 = 500000.000000
llama_model_loader: - kv 18: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 19: general.file_type u32 = 7
llama_model_loader: - kv 20: llama.vocab_size u32 = 102400
llama_model_loader: - kv 21: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 22: tokenizer.ggml.add_space_prefix bool = false
llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 24: tokenizer.ggml.pre str = default
llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,102400] = ["[PAD]", "[BOS]", "[EOS]", "[UNK]", ...
llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,102400] = [3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, ...
llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,101782] = ["t h", "Δ a", "Δ Γ", "i n", "Δ t...
llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 361
llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 32: tokenizer.chat_template str = {% for message in messages %}{% if lo...
llama_model_loader: - kv 33: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type q8_0: 226 tensors
llm_load_vocab: special tokens cache size = 362
llm_load_vocab: token to piece cache size = 0.6622 MB
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 = 102400
llm_load_print_meta: n_merges = 101782
llm_load_print_meta: vocab_only = 0
llm_load_print_meta: n_ctx_train = 4096
llm_load_print_meta: n_embd = 4096
llm_load_print_meta: n_layer = 32
llm_load_print_meta: n_head = 32
llm_load_print_meta: n_head_kv = 8
llm_load_print_meta: n_rot = 128
llm_load_print_meta: n_swa = 0
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_ctx_orig_yarn = 4096
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 = 7.82 B
llm_load_print_meta: model size = 7.74 GiB (8.50 BPW)
llm_load_print_meta: general.name = Exaone 3.0 7.8b It
llm_load_print_meta: BOS token = 1 '[BOS]'
llm_load_print_meta: EOS token = 361 '[|endofturn|]'
llm_load_print_meta: UNK token = 3 '[UNK]'
llm_load_print_meta: PAD token = 0 '[PAD]'
llm_load_print_meta: LF token = 490 'Γ'
llm_load_print_meta: EOT token = 42 '<|endoftext|>'
llm_load_print_meta: max token length = 48
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: yes
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA L4, compute capability 8.9, VMM: yes
llm_load_tensors: ggml ctx size = 0.14 MiB
llm_load_tensors: offloading 0 repeating layers to GPU
llm_load_tensors: offloaded 0/33 layers to GPU
llm_load_tensors: CPU buffer size = 7923.02 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 = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CUDA_Host KV buffer size = 64.00 MiB
llama_new_context_with_model: KV self size = 64.00 MiB, K (f16): 32.00 MiB, V (f16): 32.00 MiB
llama_new_context_with_model: CUDA_Host output buffer size = 0.39 MiB
llama_new_context_with_model: CUDA0 compute buffer size = 633.00 MiB
llama_new_context_with_model: CUDA_Host compute buffer size = 9.01 MiB
llama_new_context_with_model: graph nodes = 1030
llama_new_context_with_model: graph splits = 356
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 = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
Model metadata: {'tokenizer.ggml.unknown_token_id': '3', 'tokenizer.ggml.eos_token_id': '361', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'gpt2', 'tokenizer.ggml.add_space_prefix': 'false', 'llama.rope.dimension_count': '128', 'llama.vocab_size': '102400', 'general.file_type': '7', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.freq_base': '500000.000000', 'tokenizer.ggml.bos_token_id': '1', 'llama.attention.head_count': '32', 'general.architecture': 'llama', 'llama.attention.head_count_kv': '8', 'llama.block_count': '32', 'tokenizer.ggml.padding_token_id': '0', 'general.basename': 'exaone-3.0', 'tokenizer.ggml.pre': 'default', 'llama.context_length': '4096', 'general.name': 'Exaone 3.0 7.8b It', 'general.type': 'model', 'general.size_label': '7.8B', 'general.finetune': 'it', 'general.license.name': 'exaone', 'tokenizer.chat_template': "{% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '[|system|][|endofturn|]\n' }}{% endif %}{{ '[|' + message['role'] + '|]' + message['content'] }}{% if message['role'] == 'user' %}{{ '\n' }}{% else %}{{ '[|endofturn|]\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|assistant|]' }}{% endif %}", 'general.license.link': 'LICENSE', 'general.license': 'other', 'llama.feed_forward_length': '14336', 'llama.embedding_length': '4096'}
Available chat formats from metadata: chat_template.default
Using gguf chat template: {% for message in messages %}{% if loop.first and message['role'] != 'system' %}{{ '[|system|][|endofturn|]
' }}{% endif %}{{ '[|' + message['role'] + '|]' + message['content'] }}{% if message['role'] == 'user' %}{{ '
' }}{% else %}{{ '[|endofturn|]
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '[|assistant|]' }}{% endif %}
Using chat eos_token: [|endofturn|]
Using chat bos_token: [BOS]
llm.create_chat_completion(
messages = [
{
"role": "system",
"content": "You are EXAONE model from LG AI Research, a helpful assistant."
},
{
"role": "user",
"content": "λ€ ν΄μ€¬μμ"
}
]
)
llama_print_timings: load time = 1812.86 ms
llama_print_timings: sample time = 20.39 ms / 220 runs ( 0.09 ms per token, 10788.54 tokens per second)
llama_print_timings: prompt eval time = 1812.72 ms / 38 tokens ( 47.70 ms per token, 20.96 tokens per second)
llama_print_timings: eval time = 33280.46 ms / 219 runs ( 151.97 ms per token, 6.58 tokens per second)
llama_print_timings: total time = 35397.95 ms / 257 tokens
{'id': 'chatcmpl-451b0538-c70d-45f4-924b-106f5ac3c02f',
'object': 'chat.completion',
'created': 1723204952,
'model': '/root/.cache/huggingface/hub/models--Bingsu--exaone-3.0-7.8b-it/snapshots/c7b9c43a7d1db6509b40e9b18f10ae0554b3d4cb/./exaone-3.0-7.8B-it-Q8_0.gguf',
'choices': [{'index': 0,
'message': {'role': 'assistant',
'content': 'λ€, μκ² μ΅λλ€. μ΄μ μ λ§μνμ λ΄μ©μ μμ½ν΄ λλ¦¬κ² μ΅λλ€:\n\n1. EXAONE 2.0 λͺ¨λΈμ νΉμ§:\n - 7.8B instruction νλ νλΌλ―Έν°\n - νκ΅μ΄μ μμ΄μμ μ°μν μ±λ₯\n - λ€μν μμ
μμ λμ μ νλ\n\n2. μ°κ΅¬ λ
Όλ¬Έ:\n - "EXAONE 2.0: An Open-Retrieval Large Language Model for Dense Retrieval and Question Answering"\n\n3. μ£Όμ μ±κ³Ό:\n - νκ΅μ΄μ μμ΄μμ μ°μν μ±λ₯\n - λ€μν μμ
μμ λμ μ νλ\n\n4. νμ© μ¬λ‘:\n - κ³ κ° μ§μ μ±λ΄\n - λ²λ₯ λ¬Έμ μμ½\n - μλ£ μ 보 μ 곡\n\n5. κΈ°μ μ μΈλΆ μ¬ν:\n - 7.8B instruction νλ νλΌλ―Έν°\n - νκ΅μ΄μ μμ΄μμ μ°μν μ±λ₯\n - λ€μν μμ
μμ λμ μ νλ\n\nμ΄ μΈμ μΆκ°λ‘ κΆκΈν μ¬νμ΄ μμΌμλ©΄ μΈμ λ μ§ λ§μν΄ μ£ΌμΈμ!'},
'logprobs': None,
'finish_reason': 'stop'}],
'usage': {'prompt_tokens': 38, 'completion_tokens': 219, 'total_tokens': 257}}