efort
/
glm4
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
glm4/README_en.md

376 lines
24 KiB
Markdown
Raw Normal View History

init commit
2024-06-05 10:22:16 +08:00
# GLM-4
<p align="center">
update report
2024-06-20 11:33:05 +08:00
📄<a href="https://arxiv.org/pdf/2406.12793" target="_blank"> Report </a> • 🤗 <a href="https://huggingface.co/collections/THUDM/glm-4-665fcf188c414b03c2f7e3b7" target="_blank">HF Repo</a> • 🤖 <a href="https://modelscope.cn/models/ZhipuAI/glm-4-9b-chat" target="_blank">ModelScope</a> • 🟣 <a href="https://wisemodel.cn/models/ZhipuAI/glm-4-9b-chat" target="_blank">WiseModel</a> • 🐦 <a href="https://twitter.com/thukeg" target="_blank">Twitter</a> • 👋 Join <a href="https://discord.gg/fK2dz4bg" target="_blank">Discord</a> and <a href="resources/WECHAT.md" target="_blank">WeChat</a>
init commit
2024-06-05 10:22:16 +08:00
</p>
<p align="center">
模型体验地址更新
2024-06-05 11:14:36 +08:00
📍Experience and use a larger-scale GLM business model on the <a href="https://open.bigmodel.cn/?utm_campaign=open&_channel_track_key=OWTVNma9">Zhipu AI Open Platform</a>
init commit
2024-06-05 10:22:16 +08:00
</p>
update report
2024-06-20 11:33:05 +08:00
## Update
comment with trust_remote_code=True
2024-11-01 18:49:55 +08:00
- 🔥🔥 **News**: ```2024/11/01```: Dependencies have been updated in this repository. Please update the dependencies in
`requirements.txt` to ensure the model runs correctly. The model weights
change of readme and req for vllm new version
2024-11-18 10:10:43 +08:00
for [glm-4-9b-chat-hf](https://huggingface.co/THUDM/glm-4-9b-chat-hf) are compatible with `transformers>=4.46.2` and can
be implemented using the `GlmModel` class in the `transformers` library. Additionally, `tokenizer_chatglm.py`
comment with trust_remote_code=True
2024-11-01 18:49:55 +08:00
in [glm-4-9b-chat](https://huggingface.co/THUDM/glm-4-9b-chat) and [glm-4v-9b](https://huggingface.co/THUDM/glm-4v-9b)
has been updated for the latest version of `transformers`. Please update the files on HuggingFace.
- 🔥 **News**: ```2024/10/27```: We have open-sourced [LongReward](https://github.com/THUDM/LongReward), a model that
uses AI feedback to enhance long-context large language models.
- 🔥 **News**: ```2024/10/25```: We have open-sourced the end-to-end Mandarin-English voice dialogue
model [GLM-4-Voice](https://github.com/THUDM/GLM-4-Voice).
- 🔥 **News**: ```2024/09/05```: We have open-sourced [longcite-glm4-9b](https://huggingface.co/THUDM/LongCite-glm4-9b),
a model enabling LLMs to produce fine-grained citations in long-context Q&A, along with the
dataset [LongCite-45k](https://huggingface.co/datasets/THUDM/LongCite-45k). Try it out online
update readme
2024-09-06 15:25:16 +08:00
at [Huggingface Space](https://huggingface.co/spaces/THUDM/LongCite).
comment with trust_remote_code=True
2024-11-01 18:49:55 +08:00
- 🔥 **News**: ```2024/08/15```: We have
open-sourced [longwriter-glm4-9b](https://huggingface.co/THUDM/LongWriter-glm4-9b), a model capable of generating over
10,000 tokens in single-turn dialogue, along with the
dataset [LongWriter-6k](https://huggingface.co/datasets/THUDM/LongWriter-6k). Experience it online
at [Huggingface Space](https://huggingface.co/spaces/THUDM/LongWriter) or
the [ModelScope Community Space](https://modelscope.cn/studios/ZhipuAI/LongWriter-glm4-9b-demo).
- 🔥 **News**: ```2024/07/24```: We published the latest technical insights on long-text processing. Check out our
technical report on training the open-source GLM-4-9B model for long
texts [here](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85).
- 🔥 **News**: ```2024/07/09```: The GLM-4-9B-Chat model is now compatible
with [Ollama](https://github.com/ollama/ollama) and [Llama.cpp](https://github.com/ggerganov/llama.cpp). See detailed
information in this [PR](https://github.com/ggerganov/llama.cpp/pull/8031).
- 🔥 **News**: ```2024/06/18```: We have released a [technical report](https://arxiv.org/pdf/2406.12793), available for
viewing.
- 🔥 **News**: ```2024/06/05```: We released the GLM-4-9B series of open-source models.
update report
2024-06-20 11:33:05 +08:00
init commit
2024-06-05 10:22:16 +08:00
## 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**
update link
2024-06-05 16:24:36 +08:00
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,
ms glm-4v demo
2024-06-12 13:13:27 +08:00
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
init commit
2024-06-05 10:22:16 +08:00
context length (about 2 million Chinese characters) and the multimodal model GLM-4V-9B based on GLM-4-9B.
update link
2024-06-05 16:24:36 +08:00
**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.
init commit
2024-06-05 10:22:16 +08:00
## Model List
model download page
2024-11-01 18:52:41 +08:00
| Model | Type | Seq Length | Transformers Version | Download | Online Demo |
|:-------------------:|:----:|:----------:|:--------------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| GLM-4-9B | Base | 8K | `4.44.0 - 4.45.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-9b)<br> [🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/glm-4-9b) | / |
| GLM-4-9B-Chat | Chat | 128K | `>= 4.44.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-9b-chat)<br> [🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/GLM-4-9B-Chat) | [🤖 ModelScope CPU](https://modelscope.cn/studios/dash-infer/GLM-4-Chat-DashInfer-Demo/summary)<br> [🤖 ModelScope vLLM](https://modelscope.cn/studios/ZhipuAI/glm-4-9b-chat-vllm/summary) |
| GLM-4-9B-Chat-HF | Chat | 128K | `>= 4.46.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat-hf)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-9b-chat-hf) | [🤖 ModelScope CPU](https://modelscope.cn/studios/dash-infer/GLM-4-Chat-DashInfer-Demo/summary)<br> [🤖 ModelScope vLLM](https://modelscope.cn/studios/ZhipuAI/glm-4-9b-chat-vllm/summary) |
| GLM-4-9B-Chat-1M | Chat | 1M | `>= 4.44.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat-1m)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-9b-chat-1m)<br> [🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/GLM-4-9B-Chat-1M) | / |
| GLM-4-9B-Chat-1M-HF | Chat | 1M | `>= 4.46.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4-9b-chat-1m-hf)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4-9b-chat-1m-hf) | / |
| GLM-4V-9B | Chat | 8K | `>= 4.46.0` | [🤗 Huggingface](https://huggingface.co/THUDM/glm-4v-9b)<br> [🤖 ModelScope](https://modelscope.cn/models/ZhipuAI/glm-4v-9b)<br> [🟣 WiseModel](https://wisemodel.cn/models/ZhipuAI/GLM-4V-9B) | [🤖 ModelScope](https://modelscope.cn/studios/ZhipuAI/glm-4v-9b-Demo/summary) |
init commit
2024-06-05 10:22:16 +08:00
transformers4.46 and vllm0.6.3
2024-11-01 17:24:39 +08:00
## BenchMarkß
init commit
2024-06-05 10:22:16 +08:00
### Typical Tasks
| Model | AlignBench | MT-Bench | IFEval | MMLU | C-Eval | GSM8K | MATH | HumanEval | NaturalCodeBench |
|:--------------------|:----------:|:--------:|:------:|:----:|:------:|:-----:|:----:|:---------:|:----------------:|
| Llama-3-8B-Instruct | 6.40 | 8.00 | 68.58 | 68.4 | 51.3 | 79.6 | 30.0 | 62.2 | 24.7 |
| ChatGLM3-6B | 5.18 | 5.50 | 28.1 | 66.4 | 69.0 | 72.3 | 25.7 | 58.5 | 11.3 |
| GLM-4-9B-Chat | 7.01 | 8.35 | 69.0 | 72.4 | 75.6 | 79.6 | 50.6 | 71.8 | 32.2 |
### Base Model
| Model | MMLU | C-Eval | GPQA | GSM8K | MATH | HumanEval |
|:--------------------|:----:|:------:|:----:|:-----:|:----:|:---------:|
| Llama-3-8B | 66.6 | 51.2 | - | 45.8 | - | 33.5 |
| Llama-3-8B-Instruct | 68.4 | 51.3 | 34.2 | 79.6 | 30.0 | 62.2 |
| ChatGLM3-6B-Base | 61.4 | 69.0 | 26.8 | 72.3 | 25.7 | 58.5 |
| GLM-4-9B | 74.7 | 77.1 | 34.3 | 84.0 | 30.4 | 70.1 |
> Since `GLM-4-9B` adds some math, reasoning, and code-related instruction data during pre-training, Llama-3-8B-Instruct
> is also included in the comparison range.
### Long Context
The [needle-in-the-haystack experiment](https://github.com/LargeWorldModel/LWM/blob/main/scripts/eval_needle.py) was
conducted with a context length of 1M, and the results are as follows:
![needle](resources/eval_needle.jpeg)
The long text capability was further evaluated on LongBench-Chat, and the results are as follows:
<p align="center">
<img src="resources/longbench.png" alt="Description text" style="display: block; margin: auto; width: 65%;">
</p>
更新VLLM demo的参数
2024-06-05 11:43:08 +08:00
### Multi Language
init commit
2024-06-05 10:22:16 +08:00
update link
2024-06-05 16:24:36 +08:00
The tests for GLM-4-9B-Chat and Llama-3-8B-Instruct are conducted on six multilingual datasets. The test results and the
corresponding languages selected for each dataset are shown in the table below:
init commit
2024-06-05 10:22:16 +08:00
update link
2024-06-05 16:24:36 +08:00
| Dataset | Llama-3-8B-Instruct | GLM-4-9B-Chat | Languages |
init commit
2024-06-05 10:22:16 +08:00
|:------------|:-------------------:|:-------------:|:----------------------------------------------------------------------------------------------:|
update link
2024-06-05 16:24:36 +08:00
| M-MMLU | 49.6 | 56.6 | all |
| FLORES | 25.0 | 28.8 | ru, es, de, fr, it, pt, pl, ja, nl, ar, tr, cs, vi, fa, hu, el, ro, sv, uk, fi, ko, da, bg, no |
| MGSM | 54.0 | 65.3 | zh, en, bn, de, es, fr, ja, ru, sw, te, th |
| XWinograd | 61.7 | 73.1 | zh, en, fr, jp, ru, pt |
| XStoryCloze | 84.7 | 90.7 | zh, en, ar, es, eu, hi, id, my, ru, sw, te |
| XCOPA | 73.3 | 80.1 | zh, et, ht, id, it, qu, sw, ta, th, tr, vi |
init commit
2024-06-05 10:22:16 +08:00
### Function Call
Tested
on [Berkeley Function Calling Leaderboard](https://github.com/ShishirPatil/gorilla/tree/main/berkeley-function-call-leaderboard).
| Model | Overall Acc. | AST Summary | Exec Summary | Relevance |
|:-----------------------|:------------:|:-----------:|:------------:|:---------:|
| Llama-3-8B-Instruct | 58.88 | 59.25 | 70.01 | 45.83 |
| gpt-4-turbo-2024-04-09 | 81.24 | 82.14 | 78.61 | 88.75 |
| ChatGLM3-6B | 57.88 | 62.18 | 69.78 | 5.42 |
| GLM-4-9B-Chat | 81.00 | 80.26 | 84.40 | 87.92 |
### Multi-Modal
GLM-4V-9B is a multimodal language model with visual understanding capabilities. The evaluation results of its related
classic tasks are as follows:
| | **MMBench-EN-Test** | **MMBench-CN-Test** | **SEEDBench_IMG** | **MMStar** | **MMMU** | **MME** | **HallusionBench** | **AI2D** | **OCRBench** |
|----------------------------|---------------------|---------------------|-------------------|------------|----------|---------|--------------------|----------|--------------|
| **gpt-4o-2024-05-13** | 83.4 | 82.1 | 77.1 | 63.9 | 69.2 | 2310.3 | 55 | 84.6 | 736 |
| **gpt-4-turbo-2024-04-09** | 81.0 | 80.2 | 73.0 | 56.0 | 61.7 | 2070.2 | 43.9 | 78.6 | 656 |
| **gpt-4-1106-preview** | 77.0 | 74.4 | 72.3 | 49.7 | 53.8 | 1771.5 | 46.5 | 75.9 | 516 |
| **InternVL-Chat-V1.5** | 82.3 | 80.7 | 75.2 | 57.1 | 46.8 | 2189.6 | 47.4 | 80.6 | 720 |
| **LLaVA-Next-Yi-34B** | 81.1 | 79 | 75.7 | 51.6 | 48.8 | 2050.2 | 34.8 | 78.9 | 574 |
| **Step-1V** | 80.7 | 79.9 | 70.3 | 50.0 | 49.9 | 2206.4 | 48.4 | 79.2 | 625 |
| **MiniCPM-Llama3-V2.5** | 77.6 | 73.8 | 72.3 | 51.8 | 45.8 | 2024.6 | 42.4 | 78.4 | 725 |
| **Qwen-VL-Max** | 77.6 | 75.7 | 72.7 | 49.5 | 52 | 2281.7 | 41.2 | 75.7 | 684 |
| **Gemini 1.0 Pro** | 73.6 | 74.3 | 70.7 | 38.6 | 49 | 2148.9 | 45.7 | 72.9 | 680 |
| **Claude 3 Opus** | 63.3 | 59.2 | 64 | 45.7 | 54.9 | 1586.8 | 37.8 | 70.6 | 694 |
| **GLM-4V-9B** | 81.1 | 79.4 | 76.8 | 58.7 | 47.2 | 2163.8 | 46.6 | 81.1 | 786 |
## Quick call
xinference支持，discord链接
2024-06-06 18:13:34 +08:00
**For hardware configuration and system requirements, please check [here](basic_demo/README_en.md).**
update link
2024-06-05 16:24:36 +08:00
init commit
2024-06-05 10:22:16 +08:00
### Use the following method to quickly call the GLM-4-9B-Chat language model
Use the transformers backend for inference:
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
import os
init commit
2024-06-05 10:22:16 +08:00
model download page
2024-11-01 18:52:41 +08:00
os.environ[
'CUDA_VISIBLE_DEVICES'] = '0' # Set the GPU number. If inference with multiple GPUs, set multiple GPU numbers
transformers4.46 and vllm0.6.3
2024-11-01 17:00:39 +08:00
MODEL_PATH = "THUDM/glm-4-9b-chat-hf"
init commit
2024-06-05 10:22:16 +08:00
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
device = "cuda" if torch.cuda.is_available() else "cpu"
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)
init commit
2024-06-05 10:22:16 +08:00
query = "你好"
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(
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
MODEL_PATH,
init commit
2024-06-05 10:22:16 +08:00
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
trust_remote_code=True,
device_map="auto"
).eval()
init commit
2024-06-05 10:22:16 +08:00
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:
```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams
# GLM-4-9B-Chat
fix vllm old code to new one
2024-06-05 13:42:10 +08:00
# If you encounter OOM, you can try to reduce max_model_len or increase tp_size
init commit
2024-06-05 10:22:16 +08:00
max_model_len, tp_size = 131072, 1
transformers4.46 and vllm0.6.3
2024-11-01 17:00:39 +08:00
model_name = "THUDM/glm-4-9b-chat-hf"
fix vllm old code to new one
2024-06-05 13:42:10 +08:00
prompt = [{"role": "user", "content": "你好"}]
init commit
2024-06-05 10:22:16 +08:00
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,
fix vllm old code to new one
2024-06-05 13:42:10 +08:00
# if you encounter OOM in GLM-4-9B-Chat-1M, you can try to enable the following parameters
init commit
2024-06-05 10:22:16 +08:00
# 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)
fix vllm old code to new one
2024-06-05 13:42:10 +08:00
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)
init commit
2024-06-05 10:22:16 +08:00
```
### Use the following method to quickly call the GLM-4V-9B multimodal model
Use the transformers backend for inference:
```python
import torch
from PIL import Image
from transformers import AutoModelForCausalLM, AutoTokenizer
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
import os
init commit
2024-06-05 10:22:16 +08:00
model download page
2024-11-01 18:52:41 +08:00
os.environ[
'CUDA_VISIBLE_DEVICES'] = '0' # Set the GPU number. If inference with multiple GPUs, set multiple GPU numbers
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
MODEL_PATH = "THUDM/glm-4v-9b"
init commit
2024-06-05 10:22:16 +08:00
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
device = "cuda" if torch.cuda.is_available() else "cpu"
init commit
2024-06-05 10:22:16 +08:00
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, trust_remote_code=True)
query = '描述这张图片'
init commit
2024-06-05 10:22:16 +08:00
image = Image.open("your image").convert('RGB')
inputs = tokenizer.apply_chat_template([{"role": "user", "image": image, "content": query}],
add_generation_prompt=True, tokenize=True, return_tensors="pt",
return_dict=True) # chat mode
inputs = inputs.to(device)
model = AutoModelForCausalLM.from_pretrained(
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
MODEL_PATH,
init commit
2024-06-05 10:22:16 +08:00
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
update that multi-GPUs inference with transformers in glm-4 and glm-4v
2024-09-10 15:16:42 +08:00
trust_remote_code=True,
device_map="auto"
).eval()
init commit
2024-06-05 10:22:16 +08:00
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]))
```
Update README_en.md: Add GLM-4v-9B model support for vllm framework
2024-10-12 21:30:13 +08:00
Use the vLLM backend for inference:
```python
from PIL import Image
from vllm import LLM, SamplingParams
model_name = "THUDM/glm-4v-9b"
llm = LLM(model=model_name,
tensor_parallel_size=1,
max_model_len=8192,
trust_remote_code=True,
enforce_eager=True)
stop_token_ids = [151329, 151336, 151338]
sampling_params = SamplingParams(temperature=0.2,
max_tokens=1024,
stop_token_ids=stop_token_ids)
prompt = "What's the content of the image?"
image = Image.open("your image").convert('RGB')
inputs = {
"prompt": prompt,
"multi_modal_data": {
"image": image
model download page
2024-11-01 18:52:41 +08:00
},
}
Update README_en.md: Add GLM-4v-9B model support for vllm framework
2024-10-12 21:30:13 +08:00
outputs = llm.generate(inputs, sampling_params=sampling_params)
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
```
init commit
2024-06-05 10:22:16 +08:00
## Complete project list
If you want to learn more about the GLM-4-9B series open source models, this open source repository provides developers
with basic GLM-4-9B usage and development code through the following content
finetune and vision demo update
2024-06-07 16:53:56 +08:00
+ [basic_demo](basic_demo/README.md): Contains
Update README_en.md
2025-01-15 11:50:31 +08:00
+ Interaction code using transformers and vLLM backend
+ OpenAI API backend interaction code
+ Batch reasoning code
init commit
2024-06-05 10:22:16 +08:00
+ [composite_demo](composite_demo/README.md): Contains
Update README_en.md
2025-01-15 11:50:31 +08:00
+ Fully functional demonstration code for GLM-4-9B and GLM-4V-9B open source models, including All Tools capabilities,
long document interpretation, and multimodal capabilities.
init commit
2024-06-05 10:22:16 +08:00
+ [fintune_demo](finetune_demo/README.md): Contains
Update README_en.md
2025-01-15 11:50:31 +08:00
+ PEFT (LORA, P-Tuning) fine-tuning code
+ SFT fine-tuning code
+ [intel_device_demo](intel_device_demo/): Contains
+ OpenVINO deployment code
+ Intel® Extension for Transformers deployment code
init commit
2024-06-05 10:22:16 +08:00
update link
2024-06-05 16:24:36 +08:00
## Friendly Links
+ [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory): Efficient open-source fine-tuning framework,
already supports GLM-4-9B-Chat language model fine-tuning.
ms glm-4v demo
2024-06-12 13:13:27 +08:00
+ [SWIFT](https://github.com/modelscope/swift): LLM/VLM training framework from ModelScope, supports
更新友情链接
2024-06-26 15:34:32 +08:00
GLM-4-9B-Chat / GLM-4V-9b fine-tuning.
xinference支持，discord链接
2024-06-06 18:13:34 +08:00
+ [Xorbits Inference](https://github.com/xorbitsai/inference): Performance-enhanced and comprehensive global inference
framework, easily deploy your own models or import cutting-edge open source models with one click.
ollama
2024-07-09 18:13:59 +08:00
+ [LangChain-ChatChat](https://github.com/chatchat-space/Langchain-Chatchat): RAG and Agent applications based on
language models such as Langchain and ChatGLM
fix readme
2024-08-11 18:00:42 +08:00
+ [self-llm](https://github.com/datawhalechina/self-llm/tree/master/models/GLM-4): Datawhale's self-llm project, which
includes
xinference支持，discord链接
2024-06-06 18:13:34 +08:00
the GLM-4-9B open source model cookbook.
ollama
2024-07-09 18:13:59 +08:00
+ [chatglm.cpp](https://github.com/li-plus/chatglm.cpp): Real-time inference on your laptop accelerated by quantization,
similar to llama.cpp.
Update README_en.md
2025-01-15 11:50:31 +08:00
+ [OpenVINO](https://github.com/openvinotoolkit): glm-4-9b-chat already supports the use of OpenVINO. The toolkit accelerates inference and has a greater inference speed improvement on Intel's GPU, GPU and NPU devices. For
specific usage, please refer to [OpenVINO notebooks](https://github.com/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/llm-chatbot/llm-chatbot-generate-api.ipynb)
ms glm-4v demo
2024-06-12 13:13:27 +08:00
init commit
2024-06-05 10:22:16 +08:00
## License
+ The use of GLM-4 model weights must follow
the [Model License](https://huggingface.co/THUDM/glm-4-9b/blob/main/LICENSE).
+ The code in this open source repository follows the [Apache 2.0](LICENSE) license.
Please strictly follow the open source license.
## Reference
If you find our work helpful, please consider citing the following paper.
```
update report
2024-06-20 11:33:05 +08:00
@misc{glm2024chatglm,
title={ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools},
update readme
2024-06-20 14:17:35 +08:00
author={Team GLM and Aohan Zeng and Bin Xu and Bowen Wang and Chenhui Zhang and Da Yin and Diego Rojas and Guanyu Feng and Hanlin Zhao and Hanyu Lai and Hao Yu and Hongning Wang and Jiadai Sun and Jiajie Zhang and Jiale Cheng and Jiayi Gui and Jie Tang and Jing Zhang and Juanzi Li and Lei Zhao and Lindong Wu and Lucen Zhong and Mingdao Liu and Minlie Huang and Peng Zhang and Qinkai Zheng and Rui Lu and Shuaiqi Duan and Shudan Zhang and Shulin Cao and Shuxun Yang and Weng Lam Tam and Wenyi Zhao and Xiao Liu and Xiao Xia and Xiaohan Zhang and Xiaotao Gu and Xin Lv and Xinghan Liu and Xinyi Liu and Xinyue Yang and Xixuan Song and Xunkai Zhang and Yifan An and Yifan Xu and Yilin Niu and Yuantao Yang and Yueyan Li and Yushi Bai and Yuxiao Dong and Zehan Qi and Zhaoyu Wang and Zhen Yang and Zhengxiao Du and Zhenyu Hou and Zihan Wang},
update report
2024-06-20 11:33:05 +08:00
year={2024},
eprint={2406.12793},
archivePrefix={arXiv},
primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
init commit
2024-06-05 10:22:16 +08:00
}
```
```
@misc{wang2023cogvlm,
title={CogVLM: Visual Expert for Pretrained Language Models},
author={Weihan Wang and Qingsong Lv and Wenmeng Yu and Wenyi Hong and Ji Qi and Yan Wang and Junhui Ji and Zhuoyi Yang and Lei Zhao and Xixuan Song and Jiazheng Xu and Bin Xu and Juanzi Li and Yuxiao Dong and Ming Ding and Jie Tang},
year={2023},
eprint={2311.03079},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```