drmcbride

/

Seed-OSS-36B-Base-woSyn-Q4_K_M-GGUF

like 0

llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = seed_oss
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Seed OSS 36B Base woSyn
llama_model_loader: - kv   3:                           general.finetune str              = Base-woSyn
llama_model_loader: - kv   4:                           general.basename str              = Seed-OSS
llama_model_loader: - kv   5:                         general.size_label str              = 36B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                               general.tags arr[str,2]       = ["vllm", "text-generation"]
llama_model_loader: - kv   8:                       seed_oss.block_count u32              = 64
llama_model_loader: - kv   9:                    seed_oss.context_length u32              = 524288
llama_model_loader: - kv  10:                  seed_oss.embedding_length u32              = 5120
llama_model_loader: - kv  11:               seed_oss.feed_forward_length u32              = 27648
llama_model_loader: - kv  12:              seed_oss.attention.head_count u32              = 80
llama_model_loader: - kv  13:           seed_oss.attention.head_count_kv u32              = 8
llama_model_loader: - kv  14:                    seed_oss.rope.freq_base f32              = 10000000.000000
llama_model_loader: - kv  15:  seed_oss.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  16:              seed_oss.attention.key_length u32              = 128
llama_model_loader: - kv  17:            seed_oss.attention.value_length u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = seed-coder
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,155136]  = ["<seed:bos>", "<seed:pad>", "<seed:e...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,155136]  = [3, 3, 3, 4, 4, 4, 4, 4, 4, 3, 3, 3, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,154737]  = ["Ġ Ġ", "Ġ t", "i n", "Ġ a", "e r...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 1
llama_model_loader: - kv  26:               general.quantization_version u32              = 2
llama_model_loader: - kv  27:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 20.26 GiB (4.81 BPW) 
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'seed_oss'