Text Generation
Transformers
TensorBoard
Safetensors
PEFT
mistral
Trained with AutoTrain
text-generation-inference
Instructions to use timhoek/dolphin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timhoek/dolphin with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="timhoek/dolphin")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("timhoek/dolphin") model = AutoModelForCausalLM.from_pretrained("timhoek/dolphin", device_map="auto") - PEFT
How to use timhoek/dolphin with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use timhoek/dolphin with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "timhoek/dolphin" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "timhoek/dolphin", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/timhoek/dolphin
- SGLang
How to use timhoek/dolphin 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 "timhoek/dolphin" \ --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": "timhoek/dolphin", "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 "timhoek/dolphin" \ --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": "timhoek/dolphin", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use timhoek/dolphin with Docker Model Runner:
docker model run hf.co/timhoek/dolphin
Upload tokenizer
Browse files- tokenizer_config.json +1 -4
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -38,11 +37,9 @@
|
|
| 38 |
},
|
| 39 |
"additional_special_tokens": [],
|
| 40 |
"bos_token": "<s>",
|
| 41 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 42 |
"clean_up_tokenization_spaces": false,
|
| 43 |
"eos_token": "<|im_end|>",
|
| 44 |
-
"
|
| 45 |
-
"model_max_length": 2048,
|
| 46 |
"pad_token": "<|im_end|>",
|
| 47 |
"sp_model_kwargs": {},
|
| 48 |
"spaces_between_special_tokens": false,
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 37 |
},
|
| 38 |
"additional_special_tokens": [],
|
| 39 |
"bos_token": "<s>",
|
|
|
|
| 40 |
"clean_up_tokenization_spaces": false,
|
| 41 |
"eos_token": "<|im_end|>",
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 43 |
"pad_token": "<|im_end|>",
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"spaces_between_special_tokens": false,
|