Instructions to use solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ

SGLang

How to use solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ 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 "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ" \
    --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": "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ",
		"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 "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ" \
        --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": "solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/CerebrumDolphin-2.0-Mistral-7B-v0.2-AWQ
```

Suparious commited on Sep 3, 2024

Commit

e9b06c5

verified ·

1 Parent(s): d6552a3

Updated and moved existing to merged_models base_model tag in README.md

Browse files

Files changed (1) hide show

README.md +16 -15

README.md CHANGED Viewed

@@ -1,25 +1,16 @@
 ---
-tags:
-- mergekit
-- merge
-- quantized
-- 4-bit
-- AWQ
-- text-generation
-- autotrain_compatible
-- endpoints_compatible
-- chatml
-base_model:
-- cognitivecomputations/dolphin-2.8-mistral-7b-v02
-- Locutusque/OpenCerebrum-2.0-7B
-license: apache-2.0
 language:
 - en
 model_creator: hydra-project
 model_name: CerebrumDolphin-2.0-Mistral-7B-v0.2
 model_type: mistral
 pipeline_tag: text-generation
-inference: false
 prompt_template: '<|im_start|>system
   {system_message}<|im_end|>
@@ -32,6 +23,16 @@ prompt_template: '<|im_start|>system
   '
 quantized_by: Suparious
 ---
 # hydra-project/CerebrumDolphin-2.0-Mistral-7B-v0.2 AWQ

 ---
+base_model: Locutusque/CerebrumDolphin-2.0-Mistral-7B-v0.2
+inference: false
 language:
 - en
+license: apache-2.0
+merged_models:
+- cognitivecomputations/dolphin-2.8-mistral-7b-v02
+- Locutusque/OpenCerebrum-2.0-7B
 model_creator: hydra-project
 model_name: CerebrumDolphin-2.0-Mistral-7B-v0.2
 model_type: mistral
 pipeline_tag: text-generation
 prompt_template: '<|im_start|>system
   {system_message}<|im_end|>
   '
 quantized_by: Suparious
+tags:
+- mergekit
+- merge
+- quantized
+- 4-bit
+- AWQ
+- text-generation
+- autotrain_compatible
+- endpoints_compatible
+- chatml
 ---
 # hydra-project/CerebrumDolphin-2.0-Mistral-7B-v0.2 AWQ