Instructions to use deevade/Mistral-7B-Instruct-v0.3-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base_model, "deevade/Mistral-7B-Instruct-v0.3-finetuned")

llama-cpp-python

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deevade/Mistral-7B-Instruct-v0.3-finetuned",
	filename="Mistral-7B-Instruct-v0.3-Q4_K_M-finetuned.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Use Docker

docker model run hf.co/deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

LM Studio
Jan
Ollama
How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Ollama:
```
ollama run hf.co/deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
```

Unsloth Studio

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for deevade/Mistral-7B-Instruct-v0.3-finetuned to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for deevade/Mistral-7B-Instruct-v0.3-finetuned to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deevade/Mistral-7B-Instruct-v0.3-finetuned to start chatting

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Docker Model Runner:
```
docker model run hf.co/deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M
```

Lemonade

How to use deevade/Mistral-7B-Instruct-v0.3-finetuned with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deevade/Mistral-7B-Instruct-v0.3-finetuned:Q4_K_M

Run and chat with the model

lemonade run user.Mistral-7B-Instruct-v0.3-finetuned-Q4_K_M

List all available models

lemonade list

See axolotl config

axolotl version: 0.8.0.dev0

adapter: lora
base_model: mistralai/Mistral-7B-Instruct-v0.3
bf16: auto
bnb_config_kwargs:
  # These are default values
  llm_int8_has_fp16_weight: false
  bnb_4bit_quant_type: nf4
  bnb_4bit_use_double_quant: true
dataset_processes: 32
datasets:
- path: ./train.jsonl
  type: chat_template
  field_messages: messages
gradient_accumulation_steps: 1
gradient_checkpointing: false
learning_rate: 0.0002
lisa_layers_attribute: model.layers
load_best_model_at_end: false
lora_alpha: 16
lora_dropout: 0.05
lora_r: 8
lora_target_modules:
- q_proj
- v_proj
- k_proj
- o_proj
- gate_proj
- down_proj
- up_proj
loraplus_lr_embedding: 1.0e-06
lr_scheduler: cosine
max_prompt_len: 5012
mean_resizing_embeddings: false
micro_batch_size: 1
num_epochs: 1.0
optimizer: adamw_bnb_8bit
output_dir: ./outputs/mymodel
pretrain_multipack_attn: true
pretrain_multipack_buffer_size: 10000
qlora_sharded_model_loading: false
ray_num_workers: 1
resources_per_worker:
  GPU: 1
sample_packing_bin_size: 200
sample_packing_group_size: 100000
save_only_model: false
save_safetensors: true
sequence_len: 4096
shuffle_merged_datasets: true
skip_prepare_dataset: false
strict: false
train_on_inputs: false
trl:
  log_completions: false
  ref_model_mixup_alpha: 0.9
  ref_model_sync_steps: 64
  sync_ref_model: false
  use_vllm: false
  vllm_device: auto
  vllm_dtype: auto
  vllm_gpu_memory_utilization: 0.9
use_ray: false
val_set_size: 0.0
weight_decay: 0.0

outputs/mymodel

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the ./train.jsonl dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 27
num_epochs: 1.0

Training results

Framework versions

PEFT 0.14.0
Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 10

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for deevade/Mistral-7B-Instruct-v0.3-finetuned

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3

Adapter

(829)

this model