Instructions to use Abstract4700/talkie-1930-13b-it-hf-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abstract4700/talkie-1930-13b-it-hf-transformers with Transformers:

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

pipe = pipeline("text-generation", model="Abstract4700/talkie-1930-13b-it-hf-transformers", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Abstract4700/talkie-1930-13b-it-hf-transformers", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Abstract4700/talkie-1930-13b-it-hf-transformers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abstract4700/talkie-1930-13b-it-hf-transformers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abstract4700/talkie-1930-13b-it-hf-transformers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abstract4700/talkie-1930-13b-it-hf-transformers

SGLang

How to use Abstract4700/talkie-1930-13b-it-hf-transformers 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 "Abstract4700/talkie-1930-13b-it-hf-transformers" \
    --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": "Abstract4700/talkie-1930-13b-it-hf-transformers",
		"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 "Abstract4700/talkie-1930-13b-it-hf-transformers" \
        --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": "Abstract4700/talkie-1930-13b-it-hf-transformers",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Abstract4700/talkie-1930-13b-it-hf-transformers with Docker Model Runner:
```
docker model run hf.co/Abstract4700/talkie-1930-13b-it-hf-transformers
```

talkie-1930-13b-it Transformers Port

This repository packages talkie-lm/talkie-1930-13b-it for Hugging Face Transformers with trust_remote_code=True.

The model is a 13B decoder-only vintage language model trained on pre-1931 English-language text and instruction-tuned with pre-1931 reference-work instruction data, followed by online DPO reinforcement learning.

Usage

Install the runtime dependencies first:

pip install "transformers>=5.6.0" "accelerate>=1.0.0" "safetensors>=0.5.0" "tiktoken>=0.6.0"

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "Abstract4700/talkie-1930-13b-it-hf-transformers"

tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    trust_remote_code=True,
    dtype="bfloat16",
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Write an essay predicting what life will be like in the year 1960."}
]
inputs = tok.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
out = model.generate(inputs, max_new_tokens=300, do_sample=True, temperature=0.7)
print(tok.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))

Notes

The tokenizer is an exact tiktoken wrapper around the original vocab.txt.
The chat template is native to AutoTokenizer.apply_chat_template.
The model implements standard Transformers causal LM generation with KV caching.
The BF16 CUDA forward path mirrors the reference Talkie inference wrapper's autocast behavior internally.
generation_config.json disables top-k filtering by default to match the reference Talkie sampler defaults.
The checkpoint is stored as sharded safetensors.
Numerical parity against the reference Talkie implementation on a 195-token passage: max absolute logit difference 0.0, mean absolute logit difference 0.0.

Downloads last month: 598

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for Abstract4700/talkie-1930-13b-it-hf-transformers

Base model

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

Finetuned

talkie-lm/talkie-1930-13b-it

Finetuned

(6)

this model

Finetunes

1 model