Instructions to use xiaoningwang/talkie-1930-13b-base-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiaoningwang/talkie-1930-13b-base-hf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xiaoningwang/talkie-1930-13b-base-hf", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xiaoningwang/talkie-1930-13b-base-hf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xiaoningwang/talkie-1930-13b-base-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiaoningwang/talkie-1930-13b-base-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiaoningwang/talkie-1930-13b-base-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xiaoningwang/talkie-1930-13b-base-hf

SGLang

How to use xiaoningwang/talkie-1930-13b-base-hf 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 "xiaoningwang/talkie-1930-13b-base-hf" \
    --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": "xiaoningwang/talkie-1930-13b-base-hf",
		"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 "xiaoningwang/talkie-1930-13b-base-hf" \
        --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": "xiaoningwang/talkie-1930-13b-base-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xiaoningwang/talkie-1930-13b-base-hf with Docker Model Runner:
```
docker model run hf.co/xiaoningwang/talkie-1930-13b-base-hf
```

talkie-1930-13b-it (Transformers format)

This is a conversion of talkie-lm/talkie-1930-13b-base to the HuggingFace Transformers format. The original model was distributed as a raw PyTorch checkpoint with a custom inference library; this version can be loaded directly with AutoModelForCausalLM and AutoTokenizer.

This base model was ported to Hugging Face format by Xiaoning Wang, based on the version automatically converted by Hugging Face's ML Intern at lewtun/talkie-1930-13b-it-hf — an AI agent for ML engineering tasks. Try it yourself via the CLI or the Demo.

Model Summary
How to Use
Architecture Details
Conversion Notes
License

Model Summary

talkie-1930-13b-it is a 13B-parameter instruction-tuned language model from the talkie family, developed by Alec Radford, Nick Levine, and David Duvenaud. It was pretrained on 260B tokens of pre-1931 English-language text and instruction-tuned using a novel dataset extracted from vintage reference works — etiquette manuals, encyclopedias, letter-writing guides, and poetry collections. The model underwent reinforcement learning via online DPO with an LLM-as-a-judge to improve instruction following.

Key Features

Vintage knowledge: trained exclusively on pre-1931 text, offering a unique window into early 20th-century language and thought
Instruction-tuned: fine-tuned for conversational use with a simple chat template
13B parameters in bfloat16 (~26 GB VRAM)
2048 token context window

How to Use

Installation

This model uses custom modeling code. Make sure you have a recent version of transformers installed:

pip install -U transformers torch

Basic Generation

To be added.

Multi-turn Chat

To be added.

Chat Template

There is no chat template for this base model.

Architecture Details

talkie is a 40-layer decoder-only GPT with several distinctive architectural choices:

Component	Details
Parameters	13B
Layers	40
Attention heads	40 (MHA, no GQA)
Hidden size	5120
Head dimension	128
Intermediate size (MLP)	13696
Position encoding	RoPE (θ = 1,000,000)
Activation	SwiGLU
Normalization	RMSNorm (pre-norm)
Context length	2048
Vocabulary	65,540 (65,535 BPE + 5 special tokens)
Precision	bfloat16

Notable architectural features:

QK-normalization: RMSNorm is applied to queries and keys after RoPE
Per-head gain: learnable scalar gain per attention head, applied to queries
Embedding skip connections: each transformer block receives a residual connection from the (normalized) input embeddings
Activation gains: learnable scalar gains on attention and MLP residual streams (initialized to (2·L)^(-0.5))
lm_head weight gain: a learnable scalar applied to the output projection weights

Conversion Notes

This model was converted from the original talkie-lm/talkie-1930-13b-it PyTorch checkpoint using the reference talkie codebase as ground truth. The conversion involved:

Model weights: the .pt state dict was remapped to a PreTrainedModel subclass (TalkieForCausalLM) and saved as safetensors
Tokenizer: the tiktoken BPE vocabulary was converted to a PreTrainedTokenizerFast with the HuggingFace TikTokenConverter, including all 5 special tokens (<|endoftext|>, <|end|>, <|user|>, <|assistant|>, <|system|>)
Validation: logits were compared on 4 test prompts covering chat, system prompts, and raw completion — all top-5 decoded tokens match exactly, with cosine similarity ≥ 0.99999994

Since this is a custom architecture, loading requires trust_remote_code=True.

License

Apache 2.0 — same as the original model.

Downloads last month: 10

Safetensors

Model size

13B params

Tensor type

F32

Model tree for xiaoningwang/talkie-1930-13b-base-hf

Base model

talkie-lm/talkie-1930-13b-base

Finetuned

(13)

this model

xiaoningwang
/

talkie-1930-13b-base-hf