Instructions to use extraltodeus/Bise_7B_m37_SSRD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use extraltodeus/Bise_7B_m37_SSRD with Transformers:

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

pipe = pipeline("text-generation", model="extraltodeus/Bise_7B_m37_SSRD")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("extraltodeus/Bise_7B_m37_SSRD")
model = AutoModelForCausalLM.from_pretrained("extraltodeus/Bise_7B_m37_SSRD")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use extraltodeus/Bise_7B_m37_SSRD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "extraltodeus/Bise_7B_m37_SSRD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "extraltodeus/Bise_7B_m37_SSRD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/extraltodeus/Bise_7B_m37_SSRD

SGLang

How to use extraltodeus/Bise_7B_m37_SSRD 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 "extraltodeus/Bise_7B_m37_SSRD" \
    --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": "extraltodeus/Bise_7B_m37_SSRD",
		"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 "extraltodeus/Bise_7B_m37_SSRD" \
        --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": "extraltodeus/Bise_7B_m37_SSRD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use extraltodeus/Bise_7B_m37_SSRD with Docker Model Runner:
```
docker model run hf.co/extraltodeus/Bise_7B_m37_SSRD
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

A merge of the following models:

TheBloke_Mistral-7B-Claude-Chat-GPTQ
TheBloke_airoboros-mistral2.2-7B-GPTQ
TheBloke_ANIMA-Phi-Neptune-Mistral-7B-GPTQ
TheBloke_Arithmo-Mistral-7B-GPTQ
TheBloke_AshhLimaRP-Mistral-7B-GPTQ
TheBloke_Astrid-Mistral-7B-GPTQ
TheBloke_Autolycus-Mistral_7B-GPTQ
TheBloke_Barcenas-Mistral-7B-GPTQ
TheBloke_blossom-v3-mistral-7B-GPTQ
TheBloke_CollectiveCognition-v1.1-Mistral-7B-GPTQ
TheBloke_dolphin-2.2.1-mistral-7B-GPTQ
TheBloke_Free_Sydney_V2_Mistral_7b-GPTQ
TheBloke_Generate_Question_Mistral_7B-GPTQ
TheBloke_Hermes-Trismegistus-Mistral-7B-GPTQ
TheBloke_Karen_TheEditor_V2_CREATIVE_Mistral_7B-GPTQ
TheBloke_Kimiko-Mistral-7B-GPTQ
TheBloke_Leo-Mistral-Hessianai-7B-Chat-GPTQ
TheBloke_MetaMath-Mistral-7B-GPTQ
TheBloke_Mistral-7B-AEZAKMI-v1-GPTQ
TheBloke_mistral-7B-dpo-v5-GPTQ
TheBloke_Mistral-7B-OpenOrca-GPTQ
TheBloke_Mistral-ClaudeLimaRP-v3-7B-GPTQ
TheBloke_Mistral-Trismegistus-7B-GPTQ
TheBloke_MistralLite-7B-GPTQ
TheBloke_mistral_7b_norobots-GPTQ
TheBloke_NeuralHermes-2.5-Mistral-7B-GPTQ
TheBloke_openbuddy-mistral-7B-v13.1-GPTQ
TheBloke_OpenHermes-2.5-Mistral-7B-GPTQ
TheBloke_openinstruct-mistral-7B-GPTQ
TheBloke_PiVoT-10.7B-Mistral-v0.2-RP-GPTQ
TheBloke_saiga_mistral_7b-GPTQ
TheBloke_samantha-1.2-mistral-7B-GPTQ
TheBloke_SauerkrautLM-7B-v1-mistral-GPTQ
TheBloke_SlimOpenOrca-Mistral-7B-GPTQ
TheBloke_speechless-code-mistral-7B-v1.0-GPTQ
TheBloke_Thespis-Mistral-7B-v0.6-GPTQ
TheBloke_Writing_Partner_Mistral_7B-GPTQ

The method used was to select each value that had the smallest sum of relative absolute difference.

The config files are copies from the TheBloke_Mistral-7B-Claude-Chat-GPTQ repository.

Downloads last month: 3