Instructions to use xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf with Transformers:

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

pipe = pipeline("text-generation", model="xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-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-1930-13b-yarn-32k-from4k-step1000-tf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf

SGLang

How to use xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-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-1930-13b-yarn-32k-from4k-step1000-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-1930-13b-yarn-32k-from4k-step1000-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-1930-13b-yarn-32k-from4k-step1000-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-1930-13b-yarn-32k-from4k-step1000-tf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf with Docker Model Runner:
```
docker model run hf.co/xlr8harder/talkie-1930-13b-yarn-32k-from4k-step1000-tf
```

xlr8harder commited on Jul 9

Commit

28cbce7

verified ·

1 Parent(s): 410eeb2

Set tokenizer context limit to 32k

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -18,6 +18,6 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "model_max_length": 9223372036854775807,
   "tokenizer_class": "TalkieTokenizer"
 }

   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
+  "model_max_length": 32768,
   "tokenizer_class": "TalkieTokenizer"
 }