Instructions to use lifeofcoding/mastermax-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lifeofcoding/mastermax-7b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lifeofcoding/mastermax-7b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lifeofcoding/mastermax-7b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lifeofcoding/mastermax-7b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lifeofcoding/mastermax-7b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lifeofcoding/mastermax-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/lifeofcoding/mastermax-7b
- SGLang
How to use lifeofcoding/mastermax-7b 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 "lifeofcoding/mastermax-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lifeofcoding/mastermax-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "lifeofcoding/mastermax-7b" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lifeofcoding/mastermax-7b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use lifeofcoding/mastermax-7b with Docker Model Runner:
docker model run hf.co/lifeofcoding/mastermax-7b
Commit ·
828dab8
1
Parent(s): cf12c59
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,15 +6,39 @@ datasets:
|
|
| 6 |
---
|
| 7 |
# Mastermax 7B
|
| 8 |
|
| 9 |
-
A open source large
|
| 10 |
|
| 11 |
## Model Details
|
| 12 |
|
| 13 |
This was based on Falcon 7B and trained on additional new datasets.
|
| 14 |
|
| 15 |
-
###
|
| 16 |
-
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
|
| 20 |
|
|
|
|
| 6 |
---
|
| 7 |
# Mastermax 7B
|
| 8 |
|
| 9 |
+
A open source large language model based on Falcon-7b
|
| 10 |
|
| 11 |
## Model Details
|
| 12 |
|
| 13 |
This was based on Falcon 7B and trained on additional new datasets.
|
| 14 |
|
| 15 |
+
### Use Model
|
| 16 |
+
|
| 17 |
+
```python
|
| 18 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 19 |
+
import transformers
|
| 20 |
+
import torch
|
| 21 |
+
model = "lifeofcoding/mastermax-7b"
|
| 22 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
| 23 |
+
pipeline = transformers.pipeline(
|
| 24 |
+
"text-generation",
|
| 25 |
+
model=model,
|
| 26 |
+
tokenizer=tokenizer,
|
| 27 |
+
torch_dtype=torch.bfloat16,
|
| 28 |
+
trust_remote_code=True,
|
| 29 |
+
device_map="auto",
|
| 30 |
+
)
|
| 31 |
+
sequences = pipeline(
|
| 32 |
+
"Girafatron is obsessed with giraffes, the most glorious animal on the face of this Earth. Giraftron believes all other animals are irrelevant when compared to the glorious majesty of the giraffe.\nDaniel: Hello, Girafatron!\nGirafatron:",
|
| 33 |
+
max_length=200,
|
| 34 |
+
do_sample=True,
|
| 35 |
+
top_k=10,
|
| 36 |
+
num_return_sequences=1,
|
| 37 |
+
eos_token_id=tokenizer.eos_token_id,
|
| 38 |
+
)
|
| 39 |
+
for seq in sequences:
|
| 40 |
+
print(f"Result: {seq['generated_text']}")
|
| 41 |
+
```
|
| 42 |
|
| 43 |
|
| 44 |
|