Quantizations of https://huggingface.co/THUDM/glm-4-9b-chat

Note: To be able to use these quants, you must enable Flash Attention (-fa) or llama.cpp will crash.

Inference Clients/UIs

• llama.cpp
• JanAI
• KoboldCPP
• text-generation-webui
• ollama
• GPT4All

From original readme

Model Introduction

GLM-4-9B is the open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. In the evaluation of data sets in semantics, mathematics, reasoning, code, and knowledge, GLM-4-9B and its human preference-aligned version GLM-4-9B-Chat have shown superior performance beyond Llama-3-8B. In addition to multi-round conversations, GLM-4-9B-Chat also has advanced features such as web browsing, code execution, custom tool calls (Function Call), and long text reasoning (supporting up to 128K context). This generation of models has added multi-language support, supporting 26 languages including Japanese, Korean, and German. We have also launched the GLM-4-9B-Chat-1M model that supports 1M context length (about 2 million Chinese characters) and the multimodal model GLM-4V-9B based on GLM-4-9B. GLM-4V-9B possesses dialogue capabilities in both Chinese and English at a high resolution of 1120*1120. In various multimodal evaluations, including comprehensive abilities in Chinese and English, perception & reasoning, text recognition, and chart understanding, GLM-4V-9B demonstrates superior performance compared to GPT-4-turbo-2024-04-09, Gemini 1.0 Pro, Qwen-VL-Max, and Claude 3 Opus.

Quick Start

For more inference code and requirements, please visit our github page.

Use the following method to quickly call the GLM-4-9B-Chat language model

Use the transformers backend for inference:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda"

tokenizer = AutoTokenizer.from_pretrained("THUDM/glm-4-9b-chat", trust_remote_code=True)

query = "Hello"

inputs = tokenizer.apply_chat_template([{"role": "user", "content": query}],
                                       add_generation_prompt=True,
                                       tokenize=True,
                                       return_tensors="pt",
                                       return_dict=True
                                       )

inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
    "THUDM/glm-4-9b-chat",
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True
).to(device).eval()

gen_kwargs = {"max_length": 2500, "do_sample": True, "top_k": 1}
with torch.no_grad():
    outputs = model.generate(**inputs, **gen_kwargs)
    outputs = outputs[:, inputs['input_ids'].shape[1]:]
    print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use the vLLM backend for inference:

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

# GLM-4-9B-Chat-1M
# max_model_len, tp_size = 1048576, 4

# GLM-4-9B-Chat
# If you encounter OOM, it is recommended to reduce max_model_len or increase tp_size
max_model_len, tp_size = 131072, 1
model_name = "THUDM/glm-4-9b-chat"
prompt = [{"role": "user", "content": "hello"}]

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
llm = LLM(
    model=model_name,
    tensor_parallel_size=tp_size,
    max_model_len=max_model_len,
    trust_remote_code=True,
    enforce_eager=True,
    # GLM-4-9B-Chat-1M If you encounter OOM phenomenon, it is recommended to enable the following parameters
    # enable_chunked_prefill=True,
    # max_num_batched_tokens=8192
)
stop_token_ids = [151329, 151336, 151338]
sampling_params = SamplingParams(temperature=0.95, max_tokens=1024, stop_token_ids=stop_token_ids)

inputs = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
outputs = llm.generate(prompts=inputs, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)