Instructions to use teknium/Mistral-Trismegistus-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use teknium/Mistral-Trismegistus-7B with Transformers:

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

pipe = pipeline("text-generation", model="teknium/Mistral-Trismegistus-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("teknium/Mistral-Trismegistus-7B")
model = AutoModelForCausalLM.from_pretrained("teknium/Mistral-Trismegistus-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use teknium/Mistral-Trismegistus-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/teknium/Mistral-Trismegistus-7B

SGLang

How to use teknium/Mistral-Trismegistus-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 "teknium/Mistral-Trismegistus-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": "teknium/Mistral-Trismegistus-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 "teknium/Mistral-Trismegistus-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": "teknium/Mistral-Trismegistus-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use teknium/Mistral-Trismegistus-7B with Docker Model Runner:
```
docker model run hf.co/teknium/Mistral-Trismegistus-7B
```

Excellent model ! Asking about training details

by nps798 - opened Oct 9, 2023

Discussion

nps798

Oct 9, 2023

As title.
What are the code you use to train this model ?
I noticed it's qlora. and have viewed the wandb records.
I am doing myself qlora fine tuning but facing train loss unstable issue

What are the target_modules you use ?
What are the tokenizer parameter you use ?

My setting. which fail
Tokenizer initialization

tokenizer = AutoTokenizer.from_pretrained(
    f"{path_to_save}/tokenizer",
    model_max_length=512,
    padding_side="left",
    trust_remote_code=True,
    add_eos_token=True, 
    )

TOKENIZATION

    tokenized_full_prompt = tokenizer(full_prompt,
        truncation=True,
        max_length=512 , 
        padding=True, 
        return_tensors="pt")

---> in the trainer i use
data_collator=DataCollatorForLanguageModeling(tokenizer, mlm=False)
which will dynamically pad for my sequence

LORA

config = LoraConfig(
    r=16,
    lora_alpha=16,
    target_modules=[
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj",
        "lm_head",
    ],
...

Thannnnks a lot !

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment