Llama.cpp command-r pre-tokenizer gguf fixed
main: build = 2789 (84250014)
main: built with gcc (Ubuntu 13.2.0-4ubuntu3) 13.2.0 for x86_64-linux-gnu
main: quantizing '/gguf/c4ai-commandr-v01_a.gguf' to '/gguf/c4ai-command-r-v01-Q5_K_M.gguf' as Q5_K_M
llama_model_loader: loaded meta data with 26 key-value pairs and 322 tensors from c4ai-commandr-v01_a.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 = command-r
llama_model_loader: - kv 1: command-r.block_count u32 = 40
llama_model_loader: - kv 2: command-r.context_length u32 = 131072
llama_model_loader: - kv 3: command-r.embedding_length u32 = 8192
llama_model_loader: - kv 4: command-r.feed_forward_length u32 = 22528
llama_model_loader: - kv 5: command-r.attention.head_count u32 = 64
llama_model_loader: - kv 6: command-r.attention.head_count_kv u32 = 64
llama_model_loader: - kv 7: command-r.rope.freq_base f32 = 8000000.000000
llama_model_loader: - kv 8: command-r.attention.layer_norm_epsilon f32 = 0.000010
llama_model_loader: - kv 9: general.file_type u32 = 1
llama_model_loader: - kv 10: command-r.logit_scale f32 = 0.062500
llama_model_loader: - kv 11: command-r.rope.scaling.type str = none
llama_model_loader: - kv 12: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 13: tokenizer.ggml.pre str = command-r
llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,256000] = ["<PAD>", "<UNK>", "<CLS>", "<SEP>", ...
llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,256000] = [3, 3, 3, 3, 3, 3, 3, 3, 1, 1, 1, 1, ...
llama_model_loader: - kv 16: tokenizer.ggml.merges arr[str,253333] = ["Ġ Ġ", "Ġ t", "e r", "i n", "Ġ a...
llama_model_loader: - kv 17: tokenizer.ggml.bos_token_id u32 = 5
llama_model_loader: - kv 18: tokenizer.ggml.eos_token_id u32 = 255001
llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0
llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false
llama_model_loader: - kv 22: tokenizer.chat_template.tool_use str = {{ bos_token }}{% if messages[0]['rol...
llama_model_loader: - kv 23: tokenizer.chat_template.rag str = {{ bos_token }}{% if messages[0]['rol...
llama_model_loader: - kv 24: tokenizer.chat_templates arr[str,2] = ["rag", "tool_use"]
llama_model_loader: - kv 25: tokenizer.chat_template str = {{ bos_token }}{% if messages[0]['rol...
- Downloads last month
- 71