Text Generation
Transformers
Safetensors
qwen3
turkish
türkiye
reasoning
ai
lamapi
gemma3
next
next-x1
open-source
14b
large-language-model
llm
transformer
artificial-intelligence
machine-learning
nlp
multilingual
instruction-tuned
chat
generative-ai
optimized
trl
sft
cognitive
analytical
enterprise
conversational
text-generation-inference
Instructions to use thelamapi/next-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thelamapi/next-8b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="thelamapi/next-8b") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("thelamapi/next-8b") model = AutoModelForCausalLM.from_pretrained("thelamapi/next-8b") 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 thelamapi/next-8b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "thelamapi/next-8b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "thelamapi/next-8b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/thelamapi/next-8b
- SGLang
How to use thelamapi/next-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 "thelamapi/next-8b" \ --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": "thelamapi/next-8b", "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 "thelamapi/next-8b" \ --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": "thelamapi/next-8b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use thelamapi/next-8b with Docker Model Runner:
docker model run hf.co/thelamapi/next-8b
| {%- if not add_generation_prompt is defined %} | |
| {%- set add_generation_prompt = false %} | |
| {%- endif %} | |
| {%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %} | |
| {%- for message in messages %} | |
| {%- if message['role'] == 'system' %} | |
| {%- if ns.is_first_sp %} | |
| {%- set ns.system_prompt = ns.system_prompt + message['content'] %} | |
| {%- set ns.is_first_sp = false %} | |
| {%- else %} | |
| {%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endfor %} | |
| {#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #} | |
| {%- if tools is defined and tools is not none %} | |
| {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<|tool▁calls▁begin|><|tool▁call▁begin|>function<|tool▁sep|>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<|tool▁call▁end|><|tool▁calls▁end|>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %} | |
| {%- for tool in tools %} | |
| {%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %} | |
| {%- endfor %} | |
| {%- if ns.system_prompt|length != 0 %} | |
| {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %} | |
| {%- else %} | |
| {%- set ns.system_prompt = tool_ns.text %} | |
| {%- endif %} | |
| {%- endif %} | |
| {{- bos_token }} | |
| {{- ns.system_prompt }} | |
| {%- set last_index = (messages|length - 1) %} | |
| {%- for message in messages %} | |
| {%- set content = message['content'] %} | |
| {%- if message['role'] == 'user' %} | |
| {%- set ns.is_tool = false -%} | |
| {%- set ns.is_first = false -%} | |
| {%- set ns.is_last_user = true -%} | |
| {%- if loop.index0 == last_index %} | |
| {{- '<|User|>' + content }} | |
| {%- else %} | |
| {{- '<|User|>' + content + '<|Assistant|>'}} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if message['role'] == 'assistant' %} | |
| {%- if '</think>' in content %} | |
| {%- set content = (content.split('</think>')|last) %} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %} | |
| {%- set ns.is_last_user = false -%} | |
| {%- if ns.is_tool %} | |
| {{- '<|tool▁outputs▁end|>'}} | |
| {%- endif %} | |
| {%- set ns.is_first = false %} | |
| {%- set ns.is_tool = false -%} | |
| {%- set ns.is_output_first = true %} | |
| {%- for tool in message['tool_calls'] %} | |
| {%- set arguments = tool['function']['arguments'] %} | |
| {%- if arguments is not string %} | |
| {%- set arguments = arguments|tojson %} | |
| {%- endif %} | |
| {%- if not ns.is_first %} | |
| {%- if content is none %} | |
| {{- '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}} | |
| } | |
| {%- else %} | |
| {{- content + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}} | |
| {%- endif %} | |
| {%- set ns.is_first = true -%} | |
| {%- else %} | |
| {{- '\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<|tool▁call▁end|>'}} | |
| {%- endif %} | |
| {%- endfor %} | |
| {{- '<|tool▁calls▁end|><|end▁of▁sentence|>'}} | |
| {%- endif %} | |
| {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %} | |
| {%- set ns.is_last_user = false -%} | |
| {%- if ns.is_tool %} | |
| {{- '<|tool▁outputs▁end|>' + content + '<|end▁of▁sentence|>'}} | |
| {%- set ns.is_tool = false -%} | |
| {%- else %} | |
| {{- content + '<|end▁of▁sentence|>'}} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- if message['role'] == 'tool' %} | |
| {%- set ns.is_last_user = false -%} | |
| {%- set ns.is_tool = true -%} | |
| {%- if ns.is_output_first %} | |
| {{- '<|tool▁outputs▁begin|><|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}} | |
| {%- set ns.is_output_first = false %} | |
| {%- else %} | |
| {{- '\n<|tool▁output▁begin|>' + content + '<|tool▁output▁end|>'}} | |
| {%- endif %} | |
| {%- endif %} | |
| {%- endfor -%} | |
| {%- if ns.is_tool %} | |
| {{- '<|tool▁outputs▁end|>'}} | |
| {%- endif %} | |
| {#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #} | |
| {%- if add_generation_prompt and not ns.is_tool %} | |
| {{- '<|Assistant|>'}} | |
| {%- endif %} |