Text Generation
Transformers
Safetensors
English
llama
small
cpu
supra
v2
tiny
mini
open
open-source
text-generation-inference
Instructions to use SupraLabs/Supra-Mini-v2-0.1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra-Mini-v2-0.1M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SupraLabs/Supra-Mini-v2-0.1M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SupraLabs/Supra-Mini-v2-0.1M") model = AutoModelForCausalLM.from_pretrained("SupraLabs/Supra-Mini-v2-0.1M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SupraLabs/Supra-Mini-v2-0.1M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SupraLabs/Supra-Mini-v2-0.1M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SupraLabs/Supra-Mini-v2-0.1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SupraLabs/Supra-Mini-v2-0.1M
- SGLang
How to use SupraLabs/Supra-Mini-v2-0.1M 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 "SupraLabs/Supra-Mini-v2-0.1M" \ --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": "SupraLabs/Supra-Mini-v2-0.1M", "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 "SupraLabs/Supra-Mini-v2-0.1M" \ --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": "SupraLabs/Supra-Mini-v2-0.1M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SupraLabs/Supra-Mini-v2-0.1M with Docker Model Runner:
docker model run hf.co/SupraLabs/Supra-Mini-v2-0.1M
Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ Supra Mini v2 0.1M is a very tiny base model trained on 700 million tokens of Fi
|
|
| 34 |
- Weight Decay: 0.01
|
| 35 |
|
| 36 |
## Final Loss
|
| 37 |
-
This model reached a final train loss after 3 epochs of **4.
|
| 38 |
|
| 39 |
## Benchmarks
|
| 40 |
|
|
@@ -42,19 +42,25 @@ All benchmarks were executed using `lm-eval`.
|
|
| 42 |
|
| 43 |
| Task | Value | Random level |
|
| 44 |
| :------------ | :----------: | -----------: |
|
| 45 |
-
| Arc_Easy | 0.
|
| 46 |
-
| Wikitext |
|
| 47 |
-
| BLiMP | 0.
|
| 48 |
|
| 49 |
## Examples
|
| 50 |
**Prompt:** "Artificial intelligence is "<br>
|
| 51 |
-
**Output:**: "
|
|
|
|
|
|
|
| 52 |
<br><br>
|
| 53 |
**Prompt:** "The main concept of physics is "<br>
|
| 54 |
-
**Output:**: "
|
|
|
|
| 55 |
<br><br>
|
| 56 |
**Prompt:** "Once upon a time, "<br>
|
| 57 |
-
**Output:**: "
|
|
|
|
|
|
|
|
|
|
| 58 |
|
| 59 |
## Usage
|
| 60 |
To use our model, just run this code using HF Transformers to execute the model:
|
|
|
|
| 34 |
- Weight Decay: 0.01
|
| 35 |
|
| 36 |
## Final Loss
|
| 37 |
+
This model reached a final train loss after 3 epochs of **4.413**.
|
| 38 |
|
| 39 |
## Benchmarks
|
| 40 |
|
|
|
|
| 42 |
|
| 43 |
| Task | Value | Random level |
|
| 44 |
| :------------ | :----------: | -----------: |
|
| 45 |
+
| Arc_Easy | 0.2677 | 0.25 (25%) |
|
| 46 |
+
| Wikitext | 7.7940 | - |
|
| 47 |
+
| BLiMP | 0.5354 | 0.5 (50%) |
|
| 48 |
|
| 49 |
## Examples
|
| 50 |
**Prompt:** "Artificial intelligence is "<br>
|
| 51 |
+
**Output:**: *"Artificial intelligence is irreciously, and the diet of a battery.
|
| 52 |
+
These are also known as the following:
|
| 53 |
+
\- Foods, in the most commonly used to be taken by the priority of the South African American Modela, which was nothing for the first time. The federal government has been a wall of the world’s two moisture and the came on the national range of the Great Department of Amazonia, and the Politary Society of the Carli. This is that the Letters were the first third of the Building S"*
|
| 54 |
<br><br>
|
| 55 |
**Prompt:** "The main concept of physics is "<br>
|
| 56 |
+
**Output:**: *"The main concept of physics is utilized in the most commonly used to be achieved.
|
| 57 |
+
Chotos, an efficient for a dietary pathogene, and that are also known as a source of the molecularly. The failure wastered in the national categories of the California, and the Modela’s brought by the Florida. In the world's this time, it is not only on the sense of the first-metrial gardens, but they can be living in the task of the Political School of History (professed"*
|
| 58 |
<br><br>
|
| 59 |
**Prompt:** "Once upon a time, "<br>
|
| 60 |
+
**Output:**: *"Once upon a time, utilizing the fire.
|
| 61 |
+
The Samboard is that the lot of the bill.
|
| 62 |
+
After the day to be a widely money and in the world’s a harmful force.
|
| 63 |
+
Despite the size of the Bradese, and his owner, and he was noted by the Department of Management, and the Lord of Petersonia and the Council, which had been a destroyed on the tree, but the giving a came from the Hiska. The Great Marius and Jewish Amazon's Rich"*
|
| 64 |
|
| 65 |
## Usage
|
| 66 |
To use our model, just run this code using HF Transformers to execute the model:
|