Text Generation
Transformers
Safetensors
Upper Grand Valley Dani
llama
genomic
text-generation-inference
Instructions to use HuggingFaceBio/Carbon-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HuggingFaceBio/Carbon-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HuggingFaceBio/Carbon-8B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HuggingFaceBio/Carbon-8B") model = AutoModelForCausalLM.from_pretrained("HuggingFaceBio/Carbon-8B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use HuggingFaceBio/Carbon-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HuggingFaceBio/Carbon-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HuggingFaceBio/Carbon-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HuggingFaceBio/Carbon-8B
- SGLang
How to use HuggingFaceBio/Carbon-8B 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 "HuggingFaceBio/Carbon-8B" \ --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": "HuggingFaceBio/Carbon-8B", "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 "HuggingFaceBio/Carbon-8B" \ --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": "HuggingFaceBio/Carbon-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HuggingFaceBio/Carbon-8B with Docker Model Runner:
docker model run hf.co/HuggingFaceBio/Carbon-8B
Update README.md
Browse files
README.md
CHANGED
|
@@ -71,10 +71,10 @@ Genome-NIAH measures how well a DNA model actually *uses* its long context. See
|
|
| 71 |
|
| 72 |
| Context length | Carbon 3B (native / YaRN 4Γ) | Carbon 8B (native / YaRN 4Γ) | Evo2 7B |
|
| 73 |
|------------------------|------------------------------|------------------------------|---------|
|
| 74 |
-
| 16 k tokens (98 kbp) | 0.73 / 0.91 | 0.78 / 0.89 | 0.97 |
|
| 75 |
-
| 32 k tokens (196 kbp) | 0.55 / 0.90 | 0.69 / 0.87 | 0.95 |
|
| 76 |
-
| 64 k tokens (393 kbp) | β / 0.79 | β / 0.86 | 0.80 |
|
| 77 |
-
| 128 k tokens (786 kbp) | β / 0.27 | β / 0.65 |
|
| 78 |
|
| 79 |
Carbon-8B retrieves reliably up to its 32 k native boundary; **YaRN 4Γ** recovers most of the loss at the 32 k β 64 k boundary and extends usable retrieval to β 786 kbp.
|
| 80 |
|
|
|
|
| 71 |
|
| 72 |
| Context length | Carbon 3B (native / YaRN 4Γ) | Carbon 8B (native / YaRN 4Γ) | Evo2 7B |
|
| 73 |
|------------------------|------------------------------|------------------------------|---------|
|
| 74 |
+
| 16 k tokens (98 kbp) | 0.73 / 0.91 | 0.78 / 0.89 | **0.97** |
|
| 75 |
+
| 32 k tokens (196 kbp) | 0.55 / 0.90 | 0.69 / 0.87 | **0.95** |
|
| 76 |
+
| 64 k tokens (393 kbp) | β / 0.79 | β / **0.86** | 0.80 |
|
| 77 |
+
| 128 k tokens (786 kbp) | β / 0.27 | β / **0.65** | 0.53 |
|
| 78 |
|
| 79 |
Carbon-8B retrieves reliably up to its 32 k native boundary; **YaRN 4Γ** recovers most of the loss at the 32 k β 64 k boundary and extends usable retrieval to β 786 kbp.
|
| 80 |
|