Instructions to use xlr8harder/talkie-web-13b-base-tf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xlr8harder/talkie-web-13b-base-tf with Transformers:

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

pipe = pipeline("text-generation", model="xlr8harder/talkie-web-13b-base-tf", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xlr8harder/talkie-web-13b-base-tf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xlr8harder/talkie-web-13b-base-tf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xlr8harder/talkie-web-13b-base-tf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlr8harder/talkie-web-13b-base-tf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xlr8harder/talkie-web-13b-base-tf

SGLang

How to use xlr8harder/talkie-web-13b-base-tf 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 "xlr8harder/talkie-web-13b-base-tf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlr8harder/talkie-web-13b-base-tf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "xlr8harder/talkie-web-13b-base-tf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xlr8harder/talkie-web-13b-base-tf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xlr8harder/talkie-web-13b-base-tf with Docker Model Runner:
```
docker model run hf.co/xlr8harder/talkie-web-13b-base-tf
```

talkie-web-13b-base-tf / config.json

xlr8harder

Correct native context metadata to 4k

963f2bb verified 2 months ago

Raw

History Blame Contribute Delete

724 Bytes

	{
	"architectures": [
	"TalkieForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_talkie.TalkieConfig",
	"AutoModel": "modeling_talkie.TalkieModel",
	"AutoModelForCausalLM": "modeling_talkie.TalkieForCausalLM"
	},
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 65535,
	"head_dim": 128,
	"hidden_size": 5120,
	"max_position_embeddings": 4096,
	"model_type": "talkie",
	"n_embd": 5120,
	"n_head": 40,
	"n_layer": 40,
	"num_attention_heads": 40,
	"num_hidden_layers": 40,
	"pad_token_id": 65535,
	"rope_base": 1000000,
	"style": "base",
	"tie_word_embeddings": false,
	"transformers_version": "5.8.0",
	"use_cache": true,
	"vocab_size": 65536,
	"logit_scale": 1.0
	}