Instructions to use theprint/Mistral-7b-Instruct-v0.2-python-18k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theprint/Mistral-7b-Instruct-v0.2-python-18k", dtype="auto")

llama-cpp-python

How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theprint/Mistral-7b-Instruct-v0.2-python-18k",
	filename="lora_mistral-7b-instruct-v0.2-bnb-4bit_python18k-unsloth.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
# Run inference directly in the terminal:
llama-cli -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
# Run inference directly in the terminal:
llama-cli -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

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 theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

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 theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

Use Docker

docker model run hf.co/theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

LM Studio
Jan
Ollama
How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with Ollama:
```
ollama run hf.co/theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
```

Unsloth Studio new

How to use theprint/Mistral-7b-Instruct-v0.2-python-18k 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 theprint/Mistral-7b-Instruct-v0.2-python-18k 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 theprint/Mistral-7b-Instruct-v0.2-python-18k to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theprint/Mistral-7b-Instruct-v0.2-python-18k to start chatting

Docker Model Runner
How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with Docker Model Runner:
```
docker model run hf.co/theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0
```

Lemonade

How to use theprint/Mistral-7b-Instruct-v0.2-python-18k with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theprint/Mistral-7b-Instruct-v0.2-python-18k:Q8_0

Run and chat with the model

lemonade run user.Mistral-7b-Instruct-v0.2-python-18k-Q8_0

List all available models

lemonade list

theprint commited on Jun 10, 2024

Commit

d89bd91

verified ·

1 Parent(s): dfe2907

Trained with Unsloth

Browse files

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.bin +3 -0

adapter_config.json CHANGED Viewed

@@ -4,7 +4,7 @@
   "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
-  "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
@@ -21,12 +21,12 @@
   "revision": "unsloth",
   "target_modules": [
     "k_proj",
-    "v_proj",
     "o_proj",
     "q_proj",
     "down_proj",
-    "gate_proj",
-    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
+  "inference_mode": false,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "revision": "unsloth",
   "target_modules": [
     "k_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "q_proj",
     "down_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:64efcc4f2306b58a33498e65331aa115a3499798a218ee19b7b511d79843ebfa
+size 167934026