Instructions to use brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction with Transformers:

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

pipe = pipeline("text-generation", model="brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction")
model = AutoModelForCausalLM.from_pretrained("brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction

SGLang

How to use brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction 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 "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction" \
    --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": "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction",
		"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 "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction" \
        --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": "brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction with Docker Model Runner:
```
docker model run hf.co/brucethemoose/Capybara-Tess-Yi-34B-200K-exl2-4bpw-fiction
```

Nous-Capybara-34B and Tess-M-Creative-v1.0 merged, then quantized with exllamav2 on 200 rows (400K tokens) on a long Vicuna format chat, a sci fi story and a fantasy story. This should hopefully yield better chat performance than the default wikitext quantization.

Quantized to 4bpw, enough for ~47K context on a 24GB GPU.

The following merge config was used:

models:
  - model: /home/alpha/Storage/Models/Raw/larryvrh_Yi-34B-200K-Llamafied
    # no parameters necessary for base model
  - model: /home/alpha/Storage/Models/Raw/migtissera_Tess-M-v1.0
    parameters:
      density: 0.6
      weight: 1.0
  - model: /home/alpha/Storage/Models/Raw/Nous-Capybara-34B
    parameters:
      density: 0.6
      weight: 1.0
merge_method: ties
base_model: //home/alpha/Storage/Models/Raw/larryvrh_Yi-34B-200K-Llamafied
parameters:
  normalize: true
  int8_mask: true
dtype: float16

First exllama quantization pass:

python convert.py --in_dir /home/alpha/FastModels/Capybara-Tess-Yi-34B-200K -o /home/alpha/FastModels/Capybara-Tess-Yi-34B-200K-exl2 -om /home/alpha/FastModels/capytessmes.json --cal_dataset /home/alpha/Documents/smol.parquet -l 2048 -r 80 -ml 2048 -mr 40 -gr 40 -ss 4096 -nr -b 3.5 -hb 6

Second exllama quantization pass:

python convert.py --in_dir /home/alpha/FastModels/Capybara-Tess-Yi-34B-200K -o /home/alpha/FastModels/Capybara-Tess-Yi-34B-200K-exl2 -m /home/alpha/FastModels/capytessmes.json --cal_dataset /home/alpha/Documents/medium.parquet -l 2048 -r 200 -ml 2048 -mr 40 -gr 200 -ss 4096 -b 3.1 -hb 6 -cf /home/alpha/FastModels/Capybara-Tess-Yi-34B-200K-exl2-31bpw -nr

Both models have Vicuna syntax, so:

Prompt Format:

SYSTEM: ...
USER: ...
ASSISTANT: ...

Stop token: </s>

Credits:

https://github.com/cg123/mergekit

https://huggingface.co/NousResearch/Nous-Capybara-34B/discussions

https://huggingface.co/migtissera/Tess-M-Creative-v1.0

https://huggingface.co/larryvrh/Yi-34B-200K-Llamafied

https://huggingface.co/01-ai/Yi-34B-200K

Downloads last month: 8