BitNet Model only outputs G repeatedly in interactive mode with ggml-model-i2

When I run run_inference.py in interactive mode using the provided ggml-model-i2_s.gguf from Hugging Face, the model only outputs the character G in a loop, no matter what prompt I use.
Command used

python run_inference.py -m models/BitNet-b1.58-2B-4T/ggml-model-i2_s.gguf -p "You are a helpful assistant" -cnv
System info Ubuntu 22.04 Python 3.9 (Conda env) CPU only (no AVX support)
Is this expected with the i2_s quantized model? Could this be a tokenizer issue or metadata mismatch?
Thanks for your help!
Apr 20 '25 20:04 ksic180586
I face exact issue, running same system specification
Apr 21 '25 07:04 FuzzyDoctor
I believe that VirtualBox does not expose AVX or AVX2 instructions to the guest machine, even though the host CPU supports them (in my case: Ryzen 7 7730U).
I checked with the command: lscpu | grep avx → No output was returned in the VM, which confirms the absence of AVX support.
However, I tested under WSL2 (Windows Subsystem for Linux), and the AVX/AVX2 instructions are properly detected. I was able to successfully run BitNet.
Apr 21 '25 19:04 ksic180586
i`m running the model directly in an ubuntu server. The output of the command lscpu | grep avx returned avx, but the model only outputs G repeatedly. What else could i check?
PS: The run command logs this: llm_load_vocab: missing pre-tokenizer type, using: 'default' llm_load_vocab: llm_load_vocab: ************************************ llm_load_vocab: GENERATION QUALITY WILL BE DEGRADED! llm_load_vocab: CONSIDER REGENERATING THE MODEL llm_load_vocab: ************************************
Apr 22 '25 21:04 ronssm
On https://github.com/microsoft/BitNet: Did you properly install the required dependencies — Python (>=3.9), CMake (>=3.22), Clang (>=18), and Conda — and then follow the installation steps as described?
Apr 22 '25 23:04 ksic180586
Running Bitnet on Ubuntu 24, with Python 3.9. I'm facing the same problem, here's the inference log:
$ python3.9 run_inference.py -m models/Llama3-8B-1.58-100B-tokens/ggml-model-i2_s.gguf -p "Implement a python function to get the factorial of a number." -t 12 -n 900
warning: not compiled with GPU offload support, --gpu-layers option will be ignored
warning: see main README.md for information on enabling GPU BLAS support
build: 3957 (5eb47b72) with cc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0 for x86_64-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from models/Llama3-8B-1.58-100B-tokens/ggml-model-i2_s.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              = Llama3-8B-1.58-100B-tokens
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              = 40
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              = 128009
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: - type  f32:   65 tensors
llama_model_loader: - type  f16:    2 tensors
llama_model_loader: - type i2_s:  224 tensors
llm_load_vocab: control token: 128253 '<|begin_of_text|><|reserved_special_token_248|>' is not marked as EOG
llm_load_vocab: control token: 128252 '<|begin_of_text|><|reserved_special_token_247|>' is not marked as EOG
llm_load_vocab: control token: 128251 '<|begin_of_text|><|reserved_special_token_246|>' is not marked as EOG
llm_load_vocab: control token: 128246 '<|begin_of_text|><|reserved_special_token_241|>' is not marked as EOG
llm_load_vocab: control token: 128245 '<|begin_of_text|><|reserved_special_token_240|>' is not marked as EOG
llm_load_vocab: control token: 128244 '<|begin_of_text|><|reserved_special_token_239|>' is not marked as EOG
llm_load_vocab: control token: 128243 '<|begin_of_text|><|reserved_special_token_238|>' is not marked as EOG
llm_load_vocab: control token: 128242 '<|begin_of_text|><|reserved_special_token_237|>' is not marked as EOG
llm_load_vocab: control token: 128241 '<|begin_of_text|><|reserved_special_token_236|>' is not marked as EOG
llm_load_vocab: control token: 128240 '<|begin_of_text|><|reserved_special_token_235|>' is not marked as EOG
llm_load_vocab: control token: 128237 '<|begin_of_text|><|reserved_special_token_232|>' is not marked as EOG
llm_load_vocab: control token: 128236 '<|begin_of_text|><|reserved_special_token_231|>' is not marked as EOG
llm_load_vocab: control token: 128235 '<|begin_of_text|><|reserved_special_token_230|>' is not marked as EOG
llm_load_vocab: control token: 128234 '<|begin_of_text|><|reserved_special_token_229|>' is not marked as EOG
llm_load_vocab: control token: 128231 '<|begin_of_text|><|reserved_special_token_226|>' is not marked as EOG
llm_load_vocab: control token: 128230 '<|begin_of_text|><|reserved_special_token_225|>' is not marked as EOG
llm_load_vocab: control token: 128228 '<|begin_of_text|><|reserved_special_token_223|>' is not marked as EOG
llm_load_vocab: control token: 128226 '<|begin_of_text|><|reserved_special_token_221|>' is not marked as EOG
llm_load_vocab: control token: 128225 '<|begin_of_text|><|reserved_special_token_220|>' is not marked as EOG
llm_load_vocab: control token: 128221 '<|begin_of_text|><|reserved_special_token_216|>' is not marked as EOG
llm_load_vocab: control token: 128219 '<|begin_of_text|><|reserved_special_token_214|>' is not marked as EOG
llm_load_vocab: control token: 128218 '<|begin_of_text|><|reserved_special_token_213|>' is not marked as EOG
llm_load_vocab: control token: 128215 '<|begin_of_text|><|reserved_special_token_210|>' is not marked as EOG
llm_load_vocab: control token: 128214 '<|begin_of_text|><|reserved_special_token_209|>' is not marked as EOG
llm_load_vocab: control token: 128211 '<|begin_of_text|><|reserved_special_token_206|>' is not marked as EOG
llm_load_vocab: control token: 128209 '<|begin_of_text|><|reserved_special_token_204|>' is not marked as EOG
llm_load_vocab: control token: 128205 '<|begin_of_text|><|reserved_special_token_200|>' is not marked as EOG
llm_load_vocab: control token: 128204 '<|begin_of_text|><|reserved_special_token_199|>' is not marked as EOG
llm_load_vocab: control token: 128202 '<|begin_of_text|><|reserved_special_token_197|>' is not marked as EOG
llm_load_vocab: control token: 128200 '<|begin_of_text|><|reserved_special_token_195|>' is not marked as EOG
llm_load_vocab: control token: 128196 '<|begin_of_text|><|reserved_special_token_191|>' is not marked as EOG
llm_load_vocab: control token: 128195 '<|begin_of_text|><|reserved_special_token_190|>' is not marked as EOG
llm_load_vocab: control token: 128194 '<|begin_of_text|><|reserved_special_token_189|>' is not marked as EOG
llm_load_vocab: control token: 128193 '<|begin_of_text|><|reserved_special_token_188|>' is not marked as EOG
llm_load_vocab: control token: 128191 '<|begin_of_text|><|reserved_special_token_186|>' is not marked as EOG
llm_load_vocab: control token: 128189 '<|begin_of_text|><|reserved_special_token_184|>' is not marked as EOG
llm_load_vocab: control token: 128188 '<|begin_of_text|><|reserved_special_token_183|>' is not marked as EOG
llm_load_vocab: control token: 128187 '<|begin_of_text|><|reserved_special_token_182|>' is not marked as EOG
llm_load_vocab: control token: 128185 '<|begin_of_text|><|reserved_special_token_180|>' is not marked as EOG
llm_load_vocab: control token: 128184 '<|begin_of_text|><|reserved_special_token_179|>' is not marked as EOG
llm_load_vocab: control token: 128183 '<|begin_of_text|><|reserved_special_token_178|>' is not marked as EOG
llm_load_vocab: control token: 128181 '<|begin_of_text|><|reserved_special_token_176|>' is not marked as EOG
llm_load_vocab: control token: 128175 '<|begin_of_text|><|reserved_special_token_170|>' is not marked as EOG
llm_load_vocab: control token: 128172 '<|begin_of_text|><|reserved_special_token_167|>' is not marked as EOG
llm_load_vocab: control token: 128171 '<|begin_of_text|><|reserved_special_token_166|>' is not marked as EOG
llm_load_vocab: control token: 128170 '<|begin_of_text|><|reserved_special_token_165|>' is not marked as EOG
llm_load_vocab: control token: 128162 '<|begin_of_text|><|reserved_special_token_157|>' is not marked as EOG
llm_load_vocab: control token: 128160 '<|begin_of_text|><|reserved_special_token_155|>' is not marked as EOG
llm_load_vocab: control token: 128156 '<|begin_of_text|><|reserved_special_token_151|>' is not marked as EOG
llm_load_vocab: control token: 128155 '<|begin_of_text|><|reserved_special_token_150|>' is not marked as EOG
llm_load_vocab: control token: 128153 '<|begin_of_text|><|reserved_special_token_148|>' is not marked as EOG
llm_load_vocab: control token: 128152 '<|begin_of_text|><|reserved_special_token_147|>' is not marked as EOG
llm_load_vocab: control token: 128150 '<|begin_of_text|><|reserved_special_token_145|>' is not marked as EOG
llm_load_vocab: control token: 128148 '<|begin_of_text|><|reserved_special_token_143|>' is not marked as EOG
llm_load_vocab: control token: 128146 '<|begin_of_text|><|reserved_special_token_141|>' is not marked as EOG
llm_load_vocab: control token: 128145 '<|begin_of_text|><|reserved_special_token_140|>' is not marked as EOG
llm_load_vocab: control token: 128143 '<|begin_of_text|><|reserved_special_token_138|>' is not marked as EOG
llm_load_vocab: control token: 128141 '<|begin_of_text|><|reserved_special_token_136|>' is not marked as EOG
llm_load_vocab: control token: 128140 '<|begin_of_text|><|reserved_special_token_135|>' is not marked as EOG
llm_load_vocab: control token: 128139 '<|begin_of_text|><|reserved_special_token_134|>' is not marked as EOG
llm_load_vocab: control token: 128135 '<|begin_of_text|><|reserved_special_token_130|>' is not marked as EOG
llm_load_vocab: control token: 128133 '<|begin_of_text|><|reserved_special_token_128|>' is not marked as EOG
llm_load_vocab: control token: 128132 '<|begin_of_text|><|reserved_special_token_127|>' is not marked as EOG
llm_load_vocab: control token: 128129 '<|begin_of_text|><|reserved_special_token_124|>' is not marked as EOG
llm_load_vocab: control token: 128127 '<|begin_of_text|><|reserved_special_token_122|>' is not marked as EOG
llm_load_vocab: control token: 128126 '<|begin_of_text|><|reserved_special_token_121|>' is not marked as EOG
llm_load_vocab: control token: 128120 '<|begin_of_text|><|reserved_special_token_115|>' is not marked as EOG
llm_load_vocab: control token: 128118 '<|begin_of_text|><|reserved_special_token_113|>' is not marked as EOG
llm_load_vocab: control token: 128115 '<|begin_of_text|><|reserved_special_token_110|>' is not marked as EOG
llm_load_vocab: control token: 128113 '<|begin_of_text|><|reserved_special_token_108|>' is not marked as EOG
llm_load_vocab: control token: 128111 '<|begin_of_text|><|reserved_special_token_106|>' is not marked as EOG
llm_load_vocab: control token: 128110 '<|begin_of_text|><|reserved_special_token_105|>' is not marked as EOG
llm_load_vocab: control token: 128108 '<|begin_of_text|><|reserved_special_token_103|>' is not marked as EOG
llm_load_vocab: control token: 128107 '<|begin_of_text|><|reserved_special_token_102|>' is not marked as EOG
llm_load_vocab: control token: 128104 '<|begin_of_text|><|reserved_special_token_99|>' is not marked as EOG
llm_load_vocab: control token: 128103 '<|begin_of_text|><|reserved_special_token_98|>' is not marked as EOG
llm_load_vocab: control token: 128102 '<|begin_of_text|><|reserved_special_token_97|>' is not marked as EOG
llm_load_vocab: control token: 128101 '<|begin_of_text|><|reserved_special_token_96|>' is not marked as EOG
llm_load_vocab: control token: 128100 '<|begin_of_text|><|reserved_special_token_95|>' is not marked as EOG
llm_load_vocab: control token: 128099 '<|begin_of_text|><|reserved_special_token_94|>' is not marked as EOG
llm_load_vocab: control token: 128097 '<|begin_of_text|><|reserved_special_token_92|>' is not marked as EOG
llm_load_vocab: control token: 128096 '<|begin_of_text|><|reserved_special_token_91|>' is not marked as EOG
llm_load_vocab: control token: 128094 '<|begin_of_text|><|reserved_special_token_89|>' is not marked as EOG
llm_load_vocab: control token: 128093 '<|begin_of_text|><|reserved_special_token_88|>' is not marked as EOG
llm_load_vocab: control token: 128090 '<|begin_of_text|><|reserved_special_token_85|>' is not marked as EOG
llm_load_vocab: control token: 128086 '<|begin_of_text|><|reserved_special_token_81|>' is not marked as EOG
llm_load_vocab: control token: 128085 '<|begin_of_text|><|reserved_special_token_80|>' is not marked as EOG
llm_load_vocab: control token: 128082 '<|begin_of_text|><|reserved_special_token_77|>' is not marked as EOG
llm_load_vocab: control token: 128080 '<|begin_of_text|><|reserved_special_token_75|>' is not marked as EOG
llm_load_vocab: control token: 128077 '<|begin_of_text|><|reserved_special_token_72|>' is not marked as EOG
llm_load_vocab: control token: 128076 '<|begin_of_text|><|reserved_special_token_71|>' is not marked as EOG
llm_load_vocab: control token: 128072 '<|begin_of_text|><|reserved_special_token_67|>' is not marked as EOG
llm_load_vocab: control token: 128069 '<|begin_of_text|><|reserved_special_token_64|>' is not marked as EOG
llm_load_vocab: control token: 128068 '<|begin_of_text|><|reserved_special_token_63|>' is not marked as EOG
llm_load_vocab: control token: 128067 '<|begin_of_text|><|reserved_special_token_62|>' is not marked as EOG
llm_load_vocab: control token: 128063 '<|begin_of_text|><|reserved_special_token_58|>' is not marked as EOG
llm_load_vocab: control token: 128059 '<|begin_of_text|><|reserved_special_token_54|>' is not marked as EOG
llm_load_vocab: control token: 128058 '<|begin_of_text|><|reserved_special_token_53|>' is not marked as EOG
llm_load_vocab: control token: 128056 '<|begin_of_text|><|reserved_special_token_51|>' is not marked as EOG
llm_load_vocab: control token: 128054 '<|begin_of_text|><|reserved_special_token_49|>' is not marked as EOG
llm_load_vocab: control token: 128053 '<|begin_of_text|><|reserved_special_token_48|>' is not marked as EOG
llm_load_vocab: control token: 128051 '<|begin_of_text|><|reserved_special_token_46|>' is not marked as EOG
llm_load_vocab: control token: 128050 '<|begin_of_text|><|reserved_special_token_45|>' is not marked as EOG
llm_load_vocab: control token: 128046 '<|begin_of_text|><|reserved_special_token_41|>' is not marked as EOG
llm_load_vocab: control token: 128044 '<|begin_of_text|><|reserved_special_token_39|>' is not marked as EOG
llm_load_vocab: control token: 128043 '<|begin_of_text|><|reserved_special_token_38|>' is not marked as EOG
llm_load_vocab: control token: 128042 '<|begin_of_text|><|reserved_special_token_37|>' is not marked as EOG
llm_load_vocab: control token: 128041 '<|begin_of_text|><|reserved_special_token_36|>' is not marked as EOG
llm_load_vocab: control token: 128040 '<|begin_of_text|><|reserved_special_token_35|>' is not marked as EOG
llm_load_vocab: control token: 128036 '<|begin_of_text|><|reserved_special_token_31|>' is not marked as EOG
llm_load_vocab: control token: 128035 '<|begin_of_text|><|reserved_special_token_30|>' is not marked as EOG
llm_load_vocab: control token: 128033 '<|begin_of_text|><|reserved_special_token_28|>' is not marked as EOG
llm_load_vocab: control token: 128030 '<|begin_of_text|><|reserved_special_token_25|>' is not marked as EOG
llm_load_vocab: control token: 128029 '<|begin_of_text|><|reserved_special_token_24|>' is not marked as EOG
llm_load_vocab: control token: 128027 '<|begin_of_text|><|reserved_special_token_22|>' is not marked as EOG
llm_load_vocab: control token: 128023 '<|begin_of_text|><|reserved_special_token_18|>' is not marked as EOG
llm_load_vocab: control token: 128020 '<|begin_of_text|><|reserved_special_token_15|>' is not marked as EOG
llm_load_vocab: control token: 128019 '<|begin_of_text|><|reserved_special_token_14|>' is not marked as EOG
llm_load_vocab: control token: 128018 '<|begin_of_text|><|reserved_special_token_13|>' is not marked as EOG
llm_load_vocab: control token: 128014 '<|begin_of_text|><|reserved_special_token_9|>' is not marked as EOG
llm_load_vocab: control token: 128012 '<|begin_of_text|><|reserved_special_token_7|>' is not marked as EOG
llm_load_vocab: control token: 128008 '<|begin_of_text|><|reserved_special_token_4|>' is not marked as EOG
llm_load_vocab: control token: 128002 '<|begin_of_text|><|reserved_special_token_0|>' is not marked as EOG
llm_load_vocab: control token: 128087 '<|begin_of_text|><|reserved_special_token_82|>' is not marked as EOG
llm_load_vocab: control token: 128250 '<|begin_of_text|><|reserved_special_token_245|>' is not marked as EOG
llm_load_vocab: control token: 128116 '<|begin_of_text|><|reserved_special_token_111|>' is not marked as EOG
llm_load_vocab: control token: 128159 '<|begin_of_text|><|reserved_special_token_154|>' is not marked as EOG
llm_load_vocab: control token: 128091 '<|begin_of_text|><|reserved_special_token_86|>' is not marked as EOG
llm_load_vocab: control token: 128136 '<|begin_of_text|><|reserved_special_token_131|>' is not marked as EOG
llm_load_vocab: control token: 128028 '<|begin_of_text|><|reserved_special_token_23|>' is not marked as EOG
llm_load_vocab: control token: 128017 '<|begin_of_text|><|reserved_special_token_12|>' is not marked as EOG
llm_load_vocab: control token: 128011 '<|begin_of_text|><|reserved_special_token_6|>' is not marked as EOG
llm_load_vocab: control token: 128223 '<|begin_of_text|><|reserved_special_token_218|>' is not marked as EOG
llm_load_vocab: control token: 128147 '<|begin_of_text|><|reserved_special_token_142|>' is not marked as EOG
llm_load_vocab: control token: 128066 '<|begin_of_text|><|reserved_special_token_61|>' is not marked as EOG
llm_load_vocab: control token: 128247 '<|begin_of_text|><|reserved_special_token_242|>' is not marked as EOG
llm_load_vocab: control token: 128052 '<|begin_of_text|><|reserved_special_token_47|>' is not marked as EOG
llm_load_vocab: control token: 128169 '<|begin_of_text|><|reserved_special_token_164|>' is not marked as EOG
llm_load_vocab: control token: 128117 '<|begin_of_text|><|reserved_special_token_112|>' is not marked as EOG
llm_load_vocab: control token: 128203 '<|begin_of_text|><|reserved_special_token_198|>' is not marked as EOG
llm_load_vocab: control token: 128092 '<|begin_of_text|><|reserved_special_token_87|>' is not marked as EOG
llm_load_vocab: control token: 128071 '<|begin_of_text|><|reserved_special_token_66|>' is not marked as EOG
llm_load_vocab: control token: 128047 '<|begin_of_text|><|reserved_special_token_42|>' is not marked as EOG
llm_load_vocab: control token: 128217 '<|begin_of_text|><|reserved_special_token_212|>' is not marked as EOG
llm_load_vocab: control token: 128213 '<|begin_of_text|><|reserved_special_token_208|>' is not marked as EOG
llm_load_vocab: control token: 128249 '<|begin_of_text|><|reserved_special_token_244|>' is not marked as EOG
llm_load_vocab: control token: 128212 '<|begin_of_text|><|reserved_special_token_207|>' is not marked as EOG
llm_load_vocab: control token: 128000 '<|begin_of_text|><|begin_of_text|>' is not marked as EOG
llm_load_vocab: control token: 128075 '<|begin_of_text|><|reserved_special_token_70|>' is not marked as EOG
llm_load_vocab: control token: 128124 '<|begin_of_text|><|reserved_special_token_119|>' is not marked as EOG
llm_load_vocab: control token: 128180 '<|begin_of_text|><|reserved_special_token_175|>' is not marked as EOG
llm_load_vocab: control token: 128151 '<|begin_of_text|><|reserved_special_token_146|>' is not marked as EOG
llm_load_vocab: control token: 128079 '<|begin_of_text|><|reserved_special_token_74|>' is not marked as EOG
llm_load_vocab: control token: 128013 '<|begin_of_text|><|reserved_special_token_8|>' is not marked as EOG
llm_load_vocab: control token: 128248 '<|begin_of_text|><|reserved_special_token_243|>' is not marked as EOG
llm_load_vocab: control token: 128048 '<|begin_of_text|><|reserved_special_token_43|>' is not marked as EOG
llm_load_vocab: control token: 128034 '<|begin_of_text|><|reserved_special_token_29|>' is not marked as EOG
llm_load_vocab: control token: 128074 '<|begin_of_text|><|reserved_special_token_69|>' is not marked as EOG
llm_load_vocab: control token: 128015 '<|begin_of_text|><|reserved_special_token_10|>' is not marked as EOG
llm_load_vocab: control token: 128022 '<|begin_of_text|><|reserved_special_token_17|>' is not marked as EOG
llm_load_vocab: control token: 128081 '<|begin_of_text|><|reserved_special_token_76|>' is not marked as EOG
llm_load_vocab: control token: 128144 '<|begin_of_text|><|reserved_special_token_139|>' is not marked as EOG
llm_load_vocab: control token: 128173 '<|begin_of_text|><|reserved_special_token_168|>' is not marked as EOG
llm_load_vocab: control token: 128038 '<|begin_of_text|><|reserved_special_token_33|>' is not marked as EOG
llm_load_vocab: control token: 128138 '<|begin_of_text|><|reserved_special_token_133|>' is not marked as EOG
llm_load_vocab: control token: 128003 '<|begin_of_text|><|reserved_special_token_1|>' is not marked as EOG
llm_load_vocab: control token: 128166 '<|begin_of_text|><|reserved_special_token_161|>' is not marked as EOG
llm_load_vocab: control token: 128025 '<|begin_of_text|><|reserved_special_token_20|>' is not marked as EOG
llm_load_vocab: control token: 128178 '<|begin_of_text|><|reserved_special_token_173|>' is not marked as EOG
llm_load_vocab: control token: 128131 '<|begin_of_text|><|reserved_special_token_126|>' is not marked as EOG
llm_load_vocab: control token: 128130 '<|begin_of_text|><|reserved_special_token_125|>' is not marked as EOG
llm_load_vocab: control token: 128165 '<|begin_of_text|><|reserved_special_token_160|>' is not marked as EOG
llm_load_vocab: control token: 128149 '<|begin_of_text|><|reserved_special_token_144|>' is not marked as EOG
llm_load_vocab: control token: 128232 '<|begin_of_text|><|reserved_special_token_227|>' is not marked as EOG
llm_load_vocab: control token: 128216 '<|begin_of_text|><|reserved_special_token_211|>' is not marked as EOG
llm_load_vocab: control token: 128137 '<|begin_of_text|><|reserved_special_token_132|>' is not marked as EOG
llm_load_vocab: control token: 128055 '<|begin_of_text|><|reserved_special_token_50|>' is not marked as EOG
llm_load_vocab: control token: 128109 '<|begin_of_text|><|reserved_special_token_104|>' is not marked as EOG
llm_load_vocab: control token: 128039 '<|begin_of_text|><|reserved_special_token_34|>' is not marked as EOG
llm_load_vocab: control token: 128177 '<|begin_of_text|><|reserved_special_token_172|>' is not marked as EOG
llm_load_vocab: control token: 128176 '<|begin_of_text|><|reserved_special_token_171|>' is not marked as EOG
llm_load_vocab: control token: 128208 '<|begin_of_text|><|reserved_special_token_203|>' is not marked as EOG
llm_load_vocab: control token: 128233 '<|begin_of_text|><|reserved_special_token_228|>' is not marked as EOG
llm_load_vocab: control token: 128197 '<|begin_of_text|><|reserved_special_token_192|>' is not marked as EOG
llm_load_vocab: control token: 128061 '<|begin_of_text|><|reserved_special_token_56|>' is not marked as EOG
llm_load_vocab: control token: 128084 '<|begin_of_text|><|reserved_special_token_79|>' is not marked as EOG
llm_load_vocab: control token: 128163 '<|begin_of_text|><|reserved_special_token_158|>' is not marked as EOG
llm_load_vocab: control token: 128134 '<|begin_of_text|><|reserved_special_token_129|>' is not marked as EOG
llm_load_vocab: control token: 128224 '<|begin_of_text|><|reserved_special_token_219|>' is not marked as EOG
llm_load_vocab: control token: 128192 '<|begin_of_text|><|reserved_special_token_187|>' is not marked as EOG
llm_load_vocab: control token: 128016 '<|begin_of_text|><|reserved_special_token_11|>' is not marked as EOG
llm_load_vocab: control token: 128227 '<|begin_of_text|><|reserved_special_token_222|>' is not marked as EOG
llm_load_vocab: control token: 128199 '<|begin_of_text|><|reserved_special_token_194|>' is not marked as EOG
llm_load_vocab: control token: 128201 '<|begin_of_text|><|reserved_special_token_196|>' is not marked as EOG
llm_load_vocab: control token: 128089 '<|begin_of_text|><|reserved_special_token_84|>' is not marked as EOG
llm_load_vocab: control token: 128174 '<|begin_of_text|><|reserved_special_token_169|>' is not marked as EOG
llm_load_vocab: control token: 128049 '<|begin_of_text|><|reserved_special_token_44|>' is not marked as EOG
llm_load_vocab: control token: 128255 '<|begin_of_text|><|reserved_special_token_250|>' is not marked as EOG
llm_load_vocab: control token: 128157 '<|begin_of_text|><|reserved_special_token_152|>' is not marked as EOG
llm_load_vocab: control token: 128128 '<|begin_of_text|><|reserved_special_token_123|>' is not marked as EOG
llm_load_vocab: control token: 128083 '<|begin_of_text|><|reserved_special_token_78|>' is not marked as EOG
llm_load_vocab: control token: 128167 '<|begin_of_text|><|reserved_special_token_162|>' is not marked as EOG
llm_load_vocab: control token: 128095 '<|begin_of_text|><|reserved_special_token_90|>' is not marked as EOG
llm_load_vocab: control token: 128064 '<|begin_of_text|><|reserved_special_token_59|>' is not marked as EOG
llm_load_vocab: control token: 128164 '<|begin_of_text|><|reserved_special_token_159|>' is not marked as EOG
llm_load_vocab: control token: 128114 '<|begin_of_text|><|reserved_special_token_109|>' is not marked as EOG
llm_load_vocab: control token: 128105 '<|begin_of_text|><|reserved_special_token_100|>' is not marked as EOG
llm_load_vocab: control token: 128026 '<|begin_of_text|><|reserved_special_token_21|>' is not marked as EOG
llm_load_vocab: control token: 128112 '<|begin_of_text|><|reserved_special_token_107|>' is not marked as EOG
llm_load_vocab: control token: 128179 '<|begin_of_text|><|reserved_special_token_174|>' is not marked as EOG
llm_load_vocab: control token: 128060 '<|begin_of_text|><|reserved_special_token_55|>' is not marked as EOG
llm_load_vocab: control token: 128210 '<|begin_of_text|><|reserved_special_token_205|>' is not marked as EOG
llm_load_vocab: control token: 128186 '<|begin_of_text|><|reserved_special_token_181|>' is not marked as EOG
llm_load_vocab: control token: 128024 '<|begin_of_text|><|reserved_special_token_19|>' is not marked as EOG
llm_load_vocab: control token: 128031 '<|begin_of_text|><|reserved_special_token_26|>' is not marked as EOG
llm_load_vocab: control token: 128125 '<|begin_of_text|><|reserved_special_token_120|>' is not marked as EOG
llm_load_vocab: control token: 128161 '<|begin_of_text|><|reserved_special_token_156|>' is not marked as EOG
llm_load_vocab: control token: 128065 '<|begin_of_text|><|reserved_special_token_60|>' is not marked as EOG
llm_load_vocab: control token: 128123 '<|begin_of_text|><|reserved_special_token_118|>' is not marked as EOG
llm_load_vocab: control token: 128122 '<|begin_of_text|><|reserved_special_token_117|>' is not marked as EOG
llm_load_vocab: control token: 128007 '<|begin_of_text|><|end_header_id|>' is not marked as EOG
llm_load_vocab: control token: 128206 '<|begin_of_text|><|reserved_special_token_201|>' is not marked as EOG
llm_load_vocab: control token: 128142 '<|begin_of_text|><|reserved_special_token_137|>' is not marked as EOG
llm_load_vocab: control token: 128098 '<|begin_of_text|><|reserved_special_token_93|>' is not marked as EOG
llm_load_vocab: control token: 128021 '<|begin_of_text|><|reserved_special_token_16|>' is not marked as EOG
llm_load_vocab: control token: 128254 '<|begin_of_text|><|reserved_special_token_249|>' is not marked as EOG
llm_load_vocab: control token: 128037 '<|begin_of_text|><|reserved_special_token_32|>' is not marked as EOG
llm_load_vocab: control token: 128045 '<|begin_of_text|><|reserved_special_token_40|>' is not marked as EOG
llm_load_vocab: control token: 128190 '<|begin_of_text|><|reserved_special_token_185|>' is not marked as EOG
llm_load_vocab: control token: 128057 '<|begin_of_text|><|reserved_special_token_52|>' is not marked as EOG
llm_load_vocab: control token: 128239 '<|begin_of_text|><|reserved_special_token_234|>' is not marked as EOG
llm_load_vocab: control token: 128121 '<|begin_of_text|><|reserved_special_token_116|>' is not marked as EOG
llm_load_vocab: control token: 128222 '<|begin_of_text|><|reserved_special_token_217|>' is not marked as EOG
llm_load_vocab: control token: 128182 '<|begin_of_text|><|reserved_special_token_177|>' is not marked as EOG
llm_load_vocab: control token: 128207 '<|begin_of_text|><|reserved_special_token_202|>' is not marked as EOG
llm_load_vocab: control token: 128001 '<|begin_of_text|><|end_of_text|>' is not marked as EOG
llm_load_vocab: control token: 128088 '<|begin_of_text|><|reserved_special_token_83|>' is not marked as EOG
llm_load_vocab: control token: 128154 '<|begin_of_text|><|reserved_special_token_149|>' is not marked as EOG
llm_load_vocab: control token: 128032 '<|begin_of_text|><|reserved_special_token_27|>' is not marked as EOG
llm_load_vocab: control token: 128229 '<|begin_of_text|><|reserved_special_token_224|>' is not marked as EOG
llm_load_vocab: control token: 128238 '<|begin_of_text|><|reserved_special_token_233|>' is not marked as EOG
llm_load_vocab: control token: 128005 '<|begin_of_text|><|reserved_special_token_3|>' is not marked as EOG
llm_load_vocab: control token: 128106 '<|begin_of_text|><|reserved_special_token_101|>' is not marked as EOG
llm_load_vocab: control token: 128158 '<|begin_of_text|><|reserved_special_token_153|>' is not marked as EOG
llm_load_vocab: control token: 128062 '<|begin_of_text|><|reserved_special_token_57|>' is not marked as EOG
llm_load_vocab: control token: 128070 '<|begin_of_text|><|reserved_special_token_65|>' is not marked as EOG
llm_load_vocab: control token: 128119 '<|begin_of_text|><|reserved_special_token_114|>' is not marked as EOG
llm_load_vocab: control token: 128078 '<|begin_of_text|><|reserved_special_token_73|>' is not marked as EOG
llm_load_vocab: control token: 128004 '<|begin_of_text|><|reserved_special_token_2|>' is not marked as EOG
llm_load_vocab: control token: 128006 '<|begin_of_text|><|start_header_id|>' is not marked as EOG
llm_load_vocab: control token: 128010 '<|begin_of_text|><|reserved_special_token_5|>' is not marked as EOG
llm_load_vocab: control token: 128220 '<|begin_of_text|><|reserved_special_token_215|>' is not marked as EOG
llm_load_vocab: control token: 128073 '<|begin_of_text|><|reserved_special_token_68|>' is not marked as EOG
llm_load_vocab: control token: 128168 '<|begin_of_text|><|reserved_special_token_163|>' is not marked as EOG
llm_load_vocab: control token: 128198 '<|begin_of_text|><|reserved_special_token_193|>' is not marked as EOG
llm_load_vocab: control token: 128009 '<|begin_of_text|><|eot_id|>' is not marked as EOG
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.8041 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          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 8192
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  = 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: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = I2_S - 2 bpw ternary
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 3.58 GiB (3.83 BPW) 
llm_load_print_meta: general.name     = Llama3-8B-1.58-100B-tokens
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|><|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|begin_of_text|><|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOG token        = 128009 '<|begin_of_text|><|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: ggml ctx size =    0.14 MiB
llm_load_tensors:        CPU buffer size =  3669.02 MiB
................................................
llama_new_context_with_model: n_batch is less than GGML_KQ_MASK_PAD - increasing to 32
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: n_batch    = 32
llama_new_context_with_model: n_ubatch   = 32
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:        CPU KV buffer size =   256.00 MiB
llama_new_context_with_model: KV self size  =  256.00 MiB, K (f16):  128.00 MiB, V (f16):  128.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.49 MiB
llama_new_context_with_model:        CPU compute buffer size =    16.16 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 1
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 12

system_info: n_threads = 12 (n_threads_batch = 12) / 40 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 

sampler seed: 1710881535
sampler params: 
	repeat_last_n = 64, repeat_penalty = 1.000, 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 = 0.800
	mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampler chain: logits -> logit-bias -> penalties -> top-k -> tail-free -> typical -> top-p -> min-p -> temp-ext -> softmax -> dist 
generate: n_ctx = 2048, n_batch = 1, n_predict = 900, n_keep = 1

Implement a python function to get the factorial of a number.GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG

llama_perf_sampler_print:    sampling time =     102.44 ms /   913 runs   (    0.11 ms per token,  8912.36 tokens per second)
llama_perf_context_print:        load time =    1011.92 ms
llama_perf_context_print: prompt eval time =     671.10 ms /    13 tokens (   51.62 ms per token,    19.37 tokens per second)
llama_perf_context_print:        eval time =   48369.96 ms /   899 runs   (   53.80 ms per token,    18.59 tokens per second)
llama_perf_context_print:       total time =   49436.53 ms /   912 tokens
Any clue on what to do?