Possible (very serious) bug in chat templates that use '<s>' token having a space added after it

[jukofyork]

You can see this in my PR where I tried to add the 'alpca' chat template:

#7383

Later in the PR chat I actully copied and pasted the:

    } else if (tmpl == "deepseek" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") != std::string::npos)) {
        // deepseek-ai/deepseek-coder-33b-instruct
        for (auto message : chat) {
            std::string role(message->role);
            if (role == "system") {
                ss << message->content;
            } else if (role == "user") {
                ss << "### Instruction:\n" << message->content << "\n";
            } else if (role == "assistant") {
                ss << "### Response:\n" << message->content << "\n<|EOT|>\n";
            }
        }
        if (add_ass) {
            ss << "### Response:\n";
        }
    }

to:

    } else if (tmpl == "alpaca" || (tmpl.find("### Instruction:") != std::string::npos && tmpl.find("<|EOT|>") == std::string::npos)) {
        // deepseek-ai/deepseek-coder-33b-instruct
        for (auto message : chat) {
            std::string role(message->role);
            if (role == "system") {
                ss << message->content << "\n\n";
            } else if (role == "user") {
                ss << "### Instruction:\n" << message->content << "\n\n";
            } else if (role == "assistant") {
                ss << "### Response:\n" << message->content << "</s>\n\n";
            }
        }
        if (add_ass) {
            ss << "### Response:\n";
        }
    }

and the space between <s> and ### Instruction: persisted.

The effect of that space being added is very serious; my attempt at using phind-codellama using the deepseek chat template (with completely the wrong newlines and EOS token) actually worked much better.

[jukofyork]

I'm not even sure if it is the space that is causing it now, as this is the tokenization when using the deepseek chat template:

{"tid":"140097807843328","timestamp":1716135105,"level":"VERB","function":"update_slots","line":1955,"msg":"prompt tokenized","id_slot":0,"id_task":0,"n_ctx":16384,"n_keep":0,"n_prompt_tokens":43,"prompt_tokens":"<s> ### Instruction:\nCan you write me a C++ program to calculate logistic regression using GSL? Write a short driver in main to test it with hard coded values\n### Response:\n"}

that produces "sane" output from phind-codellama.

[jukofyork]

It was actually the extra </s>' that caused phind-codellama` to go wrong, so closing this/