zai-org

/

GLM-4.7-FP8

like 53

Follow

Z.ai 6.54k

I hosted the model via vllm and already without reasoning_parser, I found the model output with directly output without but having close tag later.

root@iv-ydzbs5zshss6ipm6s5gu /h/n/d/ark_http_proxy# curl --location 'http://localhost/v1/chat/completions' \
                                                    --header 'Authorization: Bearer YOUR_API_KEY' \
                                                    --header 'Content-Type: application/json' \
                                                    --data '{
                                                        "model": "GLM-4.7-FP8", "stream": true,
                                                        "messages": [
                                                            {
                                                                "role": "user",
                                                                "content": "what is cryptography"
                                                            }
                                                        ],"chat_template_kwargs": {"enable_thinking": true}, "skip_special_tokens": false,
                                                        "thinking": {
                                                            "type": "enabled"
                                                        },
                                                        "max_tokens": 1024,
                                                        "temperature": 1.0
                                                    }'
data: {"id":"chatcmpl-9fbc092d919f9e51","object":"chat.completion.chunk","created":1766599479,"model":"GLM-4.7-FP8","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":null},"logprobs":null,"finish_reason":null}],"prompt_token_ids":null}

data: {"id":"chatcmpl-9fbc092d919f9e51","object":"chat.completion.chunk","created":1766599479,"model":"GLM-4.7-FP8","choices":[{"index":0,"delta":{"content":"1","reasoning_content":null},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-9fbc092d919f9e51","object":"chat.completion.chunk","created":1766599479,"model":"GLM-4.7-FP8","choices":[{"index":0,"delta":{"content":". ","reasoning_content":null},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-9fbc092d919f9e51","object":"chat.completion.chunk","created":1766599479,"model":"GLM-4.7-FP8","choices":[{"index":0,"delta":{"content":" **An","reasoning_content":null},"logprobs":null,"finish_reason":null,"token_ids":null}]}

data: {"id":"chatcmpl-9fbc092d919f9e51","object":"chat.completion.chunk","created":1766599479,"model":"GLM-4.7-FP8","choices":[{"index":0,"delta":{"content":"alyze the","reasoning_content":null},"logprobs":null,"finish_reason":null,"token_ids":null}]}

I confirmed that chat template will

root@iv-ydzbs5zshss6ipm6s5gu /h/n/d/ark_http_proxy# curl -sS 'http://127.0.0.1/tokenize' \
                                                      -H 'Content-Type: application/json' \
                                                      -d '{"model":"GLM-4.7-FP8","messages":[{"role":"user","content":"hi"}],"add_generation_prompt":true,"return_token_strs":true}'
{"count":6,"max_model_len":202752,"tokens":[151331,151333,151336,6023,151337,151350],"token_strs":["[gMASK]","<sop>","<|user|>","hi","<|assistant|>","<think>"]}⏎