Text Generation
Transformers
Safetensors
English
glm4_moe_lite
causal-lm
fp8
quantization
Mixture of Experts
glm
deploypad
inference
conversational
Eval Results (legacy)
modelopt
Instructions to use Geodd/GLM-4.7-Flash-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Geodd/GLM-4.7-Flash-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Geodd/GLM-4.7-Flash-FP8") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Geodd/GLM-4.7-Flash-FP8") model = AutoModelForCausalLM.from_pretrained("Geodd/GLM-4.7-Flash-FP8", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Geodd/GLM-4.7-Flash-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Geodd/GLM-4.7-Flash-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Geodd/GLM-4.7-Flash-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Geodd/GLM-4.7-Flash-FP8
- SGLang
How to use Geodd/GLM-4.7-Flash-FP8 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Geodd/GLM-4.7-Flash-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Geodd/GLM-4.7-Flash-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Geodd/GLM-4.7-Flash-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Geodd/GLM-4.7-Flash-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Geodd/GLM-4.7-Flash-FP8 with Docker Model Runner:
docker model run hf.co/Geodd/GLM-4.7-Flash-FP8
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# GLM-4.7-Flash (FP8)
|
| 2 |
|
| 3 |
**🚀 One click deployment - coming soon on [Deploypad](https://geodd.io/)**
|
|
|
|
| 4 |
**Join our forum [Developer Forum](https://https://forum.geodd.io/)**
|
| 5 |
---
|
| 6 |
|
|
@@ -90,5 +137,5 @@ If you find our work useful in your research, please consider citing the followi
|
|
| 90 |
|
| 91 |
**Powered by [Deploypad](https://geodd.io/)**
|
| 92 |
|
| 93 |
-
* [Community Forum](https://forum.geodd.io/)
|
| 94 |
-
* [Console](https://console.geodd.io/)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: other
|
| 5 |
+
tags:
|
| 6 |
+
- text-generation
|
| 7 |
+
- causal-lm
|
| 8 |
+
- fp8
|
| 9 |
+
- quantization
|
| 10 |
+
- moe
|
| 11 |
+
- glm
|
| 12 |
+
- deploypad
|
| 13 |
+
- inference
|
| 14 |
+
library_name: transformers
|
| 15 |
+
base_model: zai-org/GLM-4.7-Flash
|
| 16 |
+
base_model_relation: quantized
|
| 17 |
+
pipeline_tag: text-generation
|
| 18 |
+
model-index:
|
| 19 |
+
- name: GLM-4.7-Flash (FP8)
|
| 20 |
+
results:
|
| 21 |
+
- task:
|
| 22 |
+
type: text-generation
|
| 23 |
+
metrics:
|
| 24 |
+
- name: AIME 25
|
| 25 |
+
type: score
|
| 26 |
+
value: 91.6
|
| 27 |
+
- name: GPQA
|
| 28 |
+
type: score
|
| 29 |
+
value: 75.2
|
| 30 |
+
- name: LCB v6
|
| 31 |
+
type: score
|
| 32 |
+
value: 64.0
|
| 33 |
+
- name: HLE
|
| 34 |
+
type: score
|
| 35 |
+
value: 14.4
|
| 36 |
+
- name: SWE-bench Verified
|
| 37 |
+
type: score
|
| 38 |
+
value: 59.2
|
| 39 |
+
- name: τ²-Bench
|
| 40 |
+
type: score
|
| 41 |
+
value: 79.5
|
| 42 |
+
- name: BrowseComp
|
| 43 |
+
type: score
|
| 44 |
+
value: 42.8
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
# GLM-4.7-Flash (FP8)
|
| 48 |
|
| 49 |
**🚀 One click deployment - coming soon on [Deploypad](https://geodd.io/)**
|
| 50 |
+
|
| 51 |
**Join our forum [Developer Forum](https://https://forum.geodd.io/)**
|
| 52 |
---
|
| 53 |
|
|
|
|
| 137 |
|
| 138 |
**Powered by [Deploypad](https://geodd.io/)**
|
| 139 |
|
| 140 |
+
* [Developer Community Forum](https://forum.geodd.io/)
|
| 141 |
+
* [Deploypad Console](https://console.geodd.io/)
|