Instructions to use mrm8488/mistral-7b-ft-h4-no_robots_instructions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrm8488/mistral-7b-ft-h4-no_robots_instructions with Transformers:

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

pipe = pipeline("text-generation", model="mrm8488/mistral-7b-ft-h4-no_robots_instructions")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrm8488/mistral-7b-ft-h4-no_robots_instructions")
model = AutoModelForCausalLM.from_pretrained("mrm8488/mistral-7b-ft-h4-no_robots_instructions", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrm8488/mistral-7b-ft-h4-no_robots_instructions with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrm8488/mistral-7b-ft-h4-no_robots_instructions"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrm8488/mistral-7b-ft-h4-no_robots_instructions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mrm8488/mistral-7b-ft-h4-no_robots_instructions

SGLang

How to use mrm8488/mistral-7b-ft-h4-no_robots_instructions 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 "mrm8488/mistral-7b-ft-h4-no_robots_instructions" \
    --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": "mrm8488/mistral-7b-ft-h4-no_robots_instructions",
		"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 "mrm8488/mistral-7b-ft-h4-no_robots_instructions" \
        --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": "mrm8488/mistral-7b-ft-h4-no_robots_instructions",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mrm8488/mistral-7b-ft-h4-no_robots_instructions with Docker Model Runner:
```
docker model run hf.co/mrm8488/mistral-7b-ft-h4-no_robots_instructions
```

Mistral 7B fine-tuned on H4/No Robots instructions

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the HuggingFaceH4/no_robots dataset for instruction following downstream task.

Training procedure

The model was loaded on 8 bits and fine-tuned on the LIMA dataset using the LoRA PEFT technique with the huggingface/peft library and trl/sft for one epoch on 1 x A100 (40GB) GPU.

SFT Trainer params:

trainer = SFTTrainer(
    model=model,
    train_dataset=train_ds,
    eval_dataset=test_ds,
    peft_config=peft_config,
    dataset_text_field="text",
    max_seq_length=2048,
    tokenizer=tokenizer,
    args=training_arguments,
    packing=False
)

LoRA config:

config = LoraConfig(
        lora_alpha=16,
        lora_dropout=0.1,
        r=64,
        bias="none",
        task_type="CAUSAL_LM",
        target_modules = ['q_proj', 'k_proj', 'down_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj']
    )

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 8
seed: 66
gradient_accumulation_steps: 64
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Step	Training Loss	Validation Loss
10	1.796200	1.774305
20	1.769700	1.679720
30	1.626800	1.667754
40	1.663400	1.665188
50	1.565700	1.659000
60	1.660300	1.658270

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

repo_id = "mrm8488/mistral-7b-ft-h4-no_robots_instructions"

model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(repo_id)

gen = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)

instruction = "[INST] Write an email to say goodbye to me boss [\INST]"
res = gen(instruction, max_new_tokens=512, temperature=0.3, top_p=0.75, top_k=40, repetition_penalty=1.2, eos_token_id=2)
print(res[0]['generated_text'])

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Citation

@misc {manuel_romero_2023,
    author       = { {Manuel Romero} },
    title        = { mistral-7b-ft-h4-no_robots_instructions (Revision 785446d) },
    year         = 2023,
    url          = { https://huggingface.co/mrm8488/mistral-7b-ft-h4-no_robots_instructions },
    doi          = { 10.57967/hf/1426 },
    publisher    = { Hugging Face }
}

Downloads last month: 13

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for mrm8488/mistral-7b-ft-h4-no_robots_instructions

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(947)

this model

mrm8488
/

mistral-7b-ft-h4-no_robots_instructions