Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use anthonymeo/full-train-b3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anthonymeo/full-train-b3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="anthonymeo/full-train-b3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("anthonymeo/full-train-b3") model = AutoModelForCausalLM.from_pretrained("anthonymeo/full-train-b3") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use anthonymeo/full-train-b3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "anthonymeo/full-train-b3" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anthonymeo/full-train-b3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/anthonymeo/full-train-b3
- SGLang
How to use anthonymeo/full-train-b3 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 "anthonymeo/full-train-b3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anthonymeo/full-train-b3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "anthonymeo/full-train-b3" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anthonymeo/full-train-b3", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use anthonymeo/full-train-b3 with Docker Model Runner:
docker model run hf.co/anthonymeo/full-train-b3
Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -2050,7 +2050,7 @@
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
-
"chat_template": "{{
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
"eos_token": "<|eot_id|>",
|
| 2056 |
"model_input_names": [
|