Instructions to use Undi95/dbrx-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Undi95/dbrx-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Undi95/dbrx-base", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Undi95/dbrx-base", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Undi95/dbrx-base", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Undi95/dbrx-base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Undi95/dbrx-base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Undi95/dbrx-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Undi95/dbrx-base
- SGLang
How to use Undi95/dbrx-base 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 "Undi95/dbrx-base" \ --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": "Undi95/dbrx-base", "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 "Undi95/dbrx-base" \ --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": "Undi95/dbrx-base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Undi95/dbrx-base with Docker Model Runner:
docker model run hf.co/Undi95/dbrx-base
Config: Explicitly set `ffn_act_fn` as `silu`| Tiktoken: Fix vocab size to include special tokens (#15)
Browse files- config.json +4 -1
- tiktoken.py +1 -1
config.json
CHANGED
|
@@ -20,7 +20,10 @@
|
|
| 20 |
"moe_jitter_eps": 0.01,
|
| 21 |
"moe_loss_weight": 0.05,
|
| 22 |
"moe_num_experts": 16,
|
| 23 |
-
"moe_top_k": 4
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
"initializer_range": 0.02,
|
| 26 |
"max_seq_len": 32768,
|
|
|
|
| 20 |
"moe_jitter_eps": 0.01,
|
| 21 |
"moe_loss_weight": 0.05,
|
| 22 |
"moe_num_experts": 16,
|
| 23 |
+
"moe_top_k": 4,
|
| 24 |
+
"ffn_act_fn": {
|
| 25 |
+
"name": "silu"
|
| 26 |
+
}
|
| 27 |
},
|
| 28 |
"initializer_range": 0.02,
|
| 29 |
"max_seq_len": 32768,
|
tiktoken.py
CHANGED
|
@@ -247,7 +247,7 @@ class TiktokenTokenizerWrapper(PreTrainedTokenizer):
|
|
| 247 |
# Get an index to add and add the item
|
| 248 |
vocab_clone[candidate_extra_id] = index_to_add
|
| 249 |
|
| 250 |
-
return vocab_clone
|
| 251 |
|
| 252 |
def _tokenize(self, text: str) -> List[str]:
|
| 253 |
"""Returns a tokenized string."""
|
|
|
|
| 247 |
# Get an index to add and add the item
|
| 248 |
vocab_clone[candidate_extra_id] = index_to_add
|
| 249 |
|
| 250 |
+
return dict(vocab_clone, **self.added_tokens_encoder)
|
| 251 |
|
| 252 |
def _tokenize(self, text: str) -> List[str]:
|
| 253 |
"""Returns a tokenized string."""
|