Instructions to use dphn/dolphin-2.6-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/dolphin-2.6-mistral-7b with Transformers:

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

pipe = pipeline("text-generation", model="dphn/dolphin-2.6-mistral-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dphn/dolphin-2.6-mistral-7b")
model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-2.6-mistral-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dphn/dolphin-2.6-mistral-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/dolphin-2.6-mistral-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dphn/dolphin-2.6-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dphn/dolphin-2.6-mistral-7b

SGLang

How to use dphn/dolphin-2.6-mistral-7b 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 "dphn/dolphin-2.6-mistral-7b" \
    --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": "dphn/dolphin-2.6-mistral-7b",
		"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 "dphn/dolphin-2.6-mistral-7b" \
        --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": "dphn/dolphin-2.6-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dphn/dolphin-2.6-mistral-7b with Docker Model Runner:
```
docker model run hf.co/dphn/dolphin-2.6-mistral-7b
```

dolphin-2.6-mistral-7b / eval.sh

ehartford

Upload eval.sh with huggingface_hub

61981cc over 2 years ago

raw

history blame contribute delete

1.32 kB

	#!/bin/bash

	MODEL_PATH="/workspace/dolphin-2.6-mistral-7b-hf"
	MODEL_NAME="dolphin-2.6-mistral-7b"
	RESULTS_PATH="/workspace/results/$MODEL_NAME"
	mkdir -p "$RESULTS_PATH"

	PRETRAINED_ARGS="$MODEL_PATH,tensor_parallel_size=4,dtype=auto,trust_remote_code=True,gpu_memory_utilization=0.8"
	MODEL_ARGS="pretrained=$PRETRAINED_ARGS"

	tasks=(
	# "mmlu"
	# "truthfulqa"
	"gsm8k"
	"hellaswag"
	"arc_challenge"
	"winogrande")

	# Function to get the number of fewshot for a given task
	get_num_fewshot() {
	case "$1" in
	"mmlu") echo 5 ;;
	"truthfulqa") echo 0 ;;
	"gsm8k") echo 5 ;;
	"hellaswag") echo 10 ;;
	"arc_challenge") echo 25 ;;
	"winogrande") echo 5 ;;
	*) echo 0 ;;
	esac
	}

	for TASK in "${tasks[@]}"; do
	echo lm_eval --model vllm --model_args "$MODEL_ARGS" --task="$TASK" --num_fewshot "$(get_num_fewshot "$TASK")" --batch_size 8 --output_path "$RESULTS_PATH/$TASK.json"
	lm_eval --model vllm --model_args "$MODEL_ARGS" --task="$TASK" --num_fewshot "$(get_num_fewshot "$TASK")" --batch_size 8 --output_path "$RESULTS_PATH/$TASK.json"
	done


	jq -s '[.[]]' $RESULTS_PATH/*.json > $RESULTS_PATH/eval_results.json

	huggingface-cli upload cognitivecomputations/$MODEL_NAME $RESULTS_PATH/eval_results.json