Closed
Description
Hello,
I am using 0.2.44. I run the following code:
from llama_cpp import Llama
llm = Llama(model_path=models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf)
I get the following output:
llama_model_loader: loaded meta data with 26 key-value pairs and 995 tensors from models/mixtral-8x7b-instruct-v0.1.Q4_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 = llama
llama_model_loader: - kv 1: general.name str = mistralai_mixtral-8x7b-instruct-v0.1
llama_model_loader: - kv 2: llama.context_length u32 = 32768
llama_model_loader: - kv 3: llama.embedding_length u32 = 4096
llama_model_loader: - kv 4: llama.block_count u32 = 32
llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128
llama_model_loader: - kv 7: llama.attention.head_count u32 = 32
llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8
llama_model_loader: - kv 9: llama.expert_count u32 = 8
llama_model_loader: - kv 10: llama.expert_used_count u32 = 2
llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 12: llama.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 13: general.file_type u32 = 15
llama_model_loader: - kv 14: tokenizer.ggml.model str = llama
llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv 16: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv 18: tokenizer.ggml.bos_token_id u32 = 1
llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 20: tokenizer.ggml.unknown_token_id u32 = 0
llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 24: tokenizer.chat_template str = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv 25: general.quantization_version u32 = 2
llama_model_loader: - type f32: 65 tensors
llama_model_loader: - type f16: 32 tensors
llama_model_loader: - type q8_0: 64 tensors
llama_model_loader: - type q4_K: 833 tensors
llama_model_loader: - type q6_K: 1 tensors
llm_load_vocab: special tokens definition check successful ( 259/32000 ).
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = llama
llm_load_print_meta: vocab type = SPM
llm_load_print_meta: n_vocab = 32000
llm_load_print_meta: n_merges = 0
llm_load_print_meta: n_ctx_train = 32768
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: n_ff = 14336
llm_load_print_meta: n_expert = 8
llm_load_print_meta: n_expert_used = 2
llm_load_print_meta: rope scaling = linear
llm_load_print_meta: freq_base_train = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx = 32768
llm_load_print_meta: rope_finetuned = unknown
llm_load_print_meta: model type = 7B
llm_load_print_meta: model ftype = Q4_K - Medium
llm_load_print_meta: model params = 46.70 B
llm_load_print_meta: model size = 24.62 GiB (4.53 BPW)
llm_load_print_meta: general.name = mistralai_mixtral-8x7b-instruct-v0.1
llm_load_print_meta: BOS token = 1 '<s>'
llm_load_print_meta: EOS token = 2 '</s>'
llm_load_print_meta: UNK token = 0 '<unk>'
llm_load_print_meta: PAD token = 0 '<unk>'
llm_load_print_meta: LF token = 13 '<0x0A>'
llm_load_tensors: ggml ctx size = 0.38 MiB
llm_load_tensors: CPU buffer size = 25215.87 MiB
....................................................................................................
llama_new_context_with_model: n_ctx = 512
llama_new_context_with_model: freq_base = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init: CPU 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: CPU input buffer size = 10.01 MiB
llama_new_context_with_model: CPU compute buffer size = 114.53 MiB
llama_new_context_with_model: graph splits (measure): 1
AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 |
Model metadata: {'tokenizer.chat_template': "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}", 'tokenizer.ggml.add_eos_token': 'false', 'tokenizer.ggml.padding_token_id': '0', 'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '15', 'general.architecture': 'llama', 'llama.rope.freq_base': '1000000.000000', 'tokenizer.ggml.add_bos_token': 'true', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '14336', 'llama.attention.layer_norm_rms_epsilon': '0.000010', 'llama.rope.dimension_count': '128', 'tokenizer.ggml.bos_token_id': '1', 'llama.attention.head_count': '32', 'llama.block_count': '32', 'llama.attention.head_count_kv': '8', 'llama.expert_count': '8', 'llama.context_length': '32768', 'general.name': 'mistralai_mixtral-8x7b-instruct-v0.1', 'llama.expert_used_count': '2'}
Using chat template: {{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}
Using chat eos_token:
Using chat bos_token:
Please note the last two lines, in which there is no chat eos_token or bos_token.
If I then run:
llm.create_chat_completion(
messages = [
{"role": "user","content": "Q: Name the planets in the solar system? A: "}
]
)
I get no response:
llama_print_timings: load time = 1252.31 ms
llama_print_timings: sample time = 0.41 ms / 1 runs ( 0.41 ms per token, 2463.05 tokens per second)
llama_print_timings: prompt eval time = 1252.16 ms / 21 tokens ( 59.63 ms per token, 16.77 tokens per second)
llama_print_timings: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second)
llama_print_timings: total time = 1255.73 ms / 22 tokens
{'id': 'chatcmpl-14e36e5b-7360-4428-a7ae-49f2b3a5d91b',
'object': 'chat.completion',
'created': 1708461563,
'model': 'models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf',
'choices': [{'index': 0,
'message': {'role': 'assistant', 'content': ''},
'finish_reason': 'stop'}],
'usage': {'prompt_tokens': 21, 'completion_tokens': 1, 'total_tokens': 22}}
On the other hand, if I run (where the only change I've made is adding the chat_format arg):
from llama_cpp import Llama
llm = Llama(model_path=models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf, chat_format="mistral-instruct")
llm.create_chat_completion(
messages = [
{"role": "user","content": "Q: Name
58BF
the planets in the solar system? A: "}
]
)
I get the expected result:
llama_print_timings: load time = 1281.79 ms
llama_print_timings: sample time = 55.94 ms / 126 runs ( 0.44 ms per token, 2252.37 tokens per second)
llama_print_timings: prompt eval time = 1281.64 ms / 22 tokens ( 58.26 ms per token, 17.17 tokens per second)
llama_print_timings: eval time = 19087.61 ms / 125 runs ( 152.70 ms per token, 6.55 tokens per second)
llama_print_timings: total time = 20728.50 ms / 147 tokens
{'id': 'chatcmpl-df42bfe7-c7a3-4f91-93ba-d7e0d801adf0',
'object': 'chat.completion',
'created': 1708461626,
'model': 'models/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf',
'choices': [{'index': 0,
'message': {'role': 'assistant',
'content': ' Sure, I\'d be happy to help with that! The solar system consists of eight planets. Here they are, listed in order of their proximity to the Sun:\n\n1. Mercury\n2. Venus\n3. Earth\n4. Mars\n5. Jupiter\n6. Saturn\n7. Uranus\n8. Neptune\n\nIt\'s worth noting that Pluto was once considered the ninth planet in our solar system, but it was reclassified as a "dwarf planet" by the International Astronomical Union in 2006.'},
'finish_reason': 'stop'}],
'usage': {'prompt_tokens': 22, 'completion_tokens': 125, 'total_tokens': 147}}
Is this possibly related to a bug in da003d8?
Metadata
Metadata
Assignees
Labels
No labels