Text Generation
Transformers
Safetensors
English
talkie
code
swe-bench
agentic
sft
conversational
custom_code
Instructions to use ricdomolm/talkie-1930-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ricdomolm/talkie-1930-coder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ricdomolm/talkie-1930-coder", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("ricdomolm/talkie-1930-coder", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ricdomolm/talkie-1930-coder with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ricdomolm/talkie-1930-coder" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ricdomolm/talkie-1930-coder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ricdomolm/talkie-1930-coder
- SGLang
How to use ricdomolm/talkie-1930-coder 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 "ricdomolm/talkie-1930-coder" \ --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": "ricdomolm/talkie-1930-coder", "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 "ricdomolm/talkie-1930-coder" \ --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": "ricdomolm/talkie-1930-coder", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ricdomolm/talkie-1930-coder with Docker Model Runner:
docker model run hf.co/ricdomolm/talkie-1930-coder
Download configuration_talkie.py from ricdomolm/talkie-1930-coder: direct link, hf CLI and curl.
- Browser
- Download file 1.35 kB
-
https://huggingface.co/ricdomolm/talkie-1930-coder/resolve/main/configuration_talkie.py
- Command line
-
hf download hf://ricdomolm/talkie-1930-coder/configuration_talkie.py
-
curl -L -o configuration_talkie.py https://huggingface.co/ricdomolm/talkie-1930-coder/resolve/main/configuration_talkie.py
1.35 kB
| """Talkie model configuration for HuggingFace Transformers.""" | |
| from transformers import PretrainedConfig | |
| class TalkieConfig(PretrainedConfig): | |
| """Configuration class for the Talkie 13B decoder-only transformer. | |
| This is a 40-layer, 40-head GPT with RoPE, SwiGLU, RMS normalisation, | |
| embedding skip connections, and per-head / per-layer gain parameters. | |
| """ | |
| model_type = "talkie" | |
| def __init__( | |
| self, | |
| vocab_size: int = 65540, | |
| hidden_size: int = 5120, | |
| intermediate_size: int = 13696, | |
| num_hidden_layers: int = 40, | |
| num_attention_heads: int = 40, | |
| head_dim: int = 128, | |
| max_position_embeddings: int = 2048, | |
| rope_theta: float = 1_000_000.0, | |
| torch_dtype: str = "bfloat16", | |
| tie_word_embeddings: bool = False, | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| self.hidden_size = hidden_size | |
| self.intermediate_size = intermediate_size | |
| self.num_hidden_layers = num_hidden_layers | |
| self.num_attention_heads = num_attention_heads | |
| self.head_dim = head_dim | |
| self.max_position_embeddings = max_position_embeddings | |
| self.rope_theta = rope_theta | |
| super().__init__( | |
| tie_word_embeddings=tie_word_embeddings, | |
| torch_dtype=torch_dtype, | |
| **kwargs, | |
| ) | |