Add DeepSeek-V3.1

[createthis]

Fixes:

llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-v3.1'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    load_model: failed to load model, '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    operator(): operator(): cleaning up before exit...   
main: exiting due to model loading error

[CISC]

Fixes:

llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-v3.1'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    load_model: failed to load model, '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    operator(): operator(): cleaning up before exit...   
main: exiting due to model loading error

Uhm, it only fixes a broken GGUF (wrong pre-tokenizer), where did that come from?

The chkhsh is identical to deepseek-v3, so no new pre-tokenizer required.

[createthis]

Fixes:

llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-v3.1'
llama_model_load_from_file_impl: failed to load model
common_init_from_params: failed to load model '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    load_model: failed to load model, '/data2/DeepSeek-V3.1-GGUF/q4_k_m/DeepSeek-V3.1-Q4_K_M.gguf'
srv    operator(): operator(): cleaning up before exit...   
main: exiting due to model loading error

Uhm, it only fixes a broken GGUF (wrong pre-tokenizer), where did that come from?

The chkhsh is identical to deepseek-v3, so no new pre-tokenizer required.

Something must be wrong with my GGUF workflow. Thanks for pointing that out.