Instructions to use afrideva/TinyMistral-248M-SFT-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use afrideva/TinyMistral-248M-SFT-v3-GGUF 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 afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf afrideva/TinyMistral-248M-SFT-v3-GGUF: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 afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/TinyMistral-248M-SFT-v3-GGUF: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 afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/TinyMistral-248M-SFT-v3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/TinyMistral-248M-SFT-v3-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/TinyMistral-248M-SFT-v3-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M

Ollama
How to use afrideva/TinyMistral-248M-SFT-v3-GGUF with Ollama:
```
ollama run hf.co/afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/TinyMistral-248M-SFT-v3-GGUF 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 afrideva/TinyMistral-248M-SFT-v3-GGUF 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 afrideva/TinyMistral-248M-SFT-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/TinyMistral-248M-SFT-v3-GGUF to start chatting

Docker Model Runner
How to use afrideva/TinyMistral-248M-SFT-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/TinyMistral-248M-SFT-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/TinyMistral-248M-SFT-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TinyMistral-248M-SFT-v3-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

afrideva commited on Dec 4, 2023

Commit

040b172

1 Parent(s): 76e599b

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +110 -0

README.md ADDED Viewed

	@@ -0,0 +1,110 @@

+---
+base_model: Felladrin/TinyMistral-248M-SFT-v3
+datasets:
+- OpenAssistant/oasst_top1_2023-08-25
+inference: false
+license: apache-2.0
+model_creator: Felladrin
+model_name: TinyMistral-248M-SFT-v3
+pipeline_tag: text-generation
+quantized_by: afrideva
+tags:
+- autotrain
+- text-generation
+- gguf
+- ggml
+- quantized
+- q2_k
+- q3_k_m
+- q4_k_m
+- q5_k_m
+- q6_k
+- q8_0
+widget:
+- text: '<|im_start|>user
+    Write the specs of a game about trolls and warriors in a fantasy world.<|im_end|>
+    <|im_start|>assistant
+    The game is an adventure game that takes place on a planet, where players must
+    explore their unique abilities to survive. Players can use different strategies
+    such as collecting items or trading them for gold or silver coins, but they also
+    need to learn how to deal with obstacles and find new ways to escape.<|im_end|>
+    <|im_start|>user
+    Could you tell me something curious about the Earth?<|im_end|>
+    <|im_start|>assistant
+    The planet is a large, rocky world with an atmosphere of 10 billion years old
+    and a surface area around 25 million miles (36 million kilometers) wide.<|im_end|>
+    <|im_start|>user
+    What are some potential applications for quantum computing?<|im_end|>
+    <|im_start|>assistant'
+---
+# Felladrin/TinyMistral-248M-SFT-v3-GGUF
+Quantized GGUF model files for [TinyMistral-248M-SFT-v3](https://huggingface.co/Felladrin/TinyMistral-248M-SFT-v3) from [Felladrin](https://huggingface.co/Felladrin)
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [tinymistral-248m-sft-v3.fp16.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.fp16.gguf) | fp16 | 497.75 MB  |
+| [tinymistral-248m-sft-v3.q2_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q2_k.gguf) | q2_k | 116.20 MB  |
+| [tinymistral-248m-sft-v3.q3_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q3_k_m.gguf) | q3_k_m | 131.01 MB  |
+| [tinymistral-248m-sft-v3.q4_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q4_k_m.gguf) | q4_k_m | 156.60 MB  |
+| [tinymistral-248m-sft-v3.q5_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q5_k_m.gguf) | q5_k_m | 180.16 MB  |
+| [tinymistral-248m-sft-v3.q6_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q6_k.gguf) | q6_k | 205.20 MB  |
+| [tinymistral-248m-sft-v3.q8_0.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v3-GGUF/resolve/main/tinymistral-248m-sft-v3.q8_0.gguf) | q8_0 | 265.26 MB  |
+## Original Model Card:
+# Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads
+- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M/blob/90b89d18fdf27937dc04ab8a9b543c5af2991c7f/README.md)
+- Dataset: [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25)
+## Recommended Prompt Format
+```
+<|im_start|>user
+{message}<|im_end|>
+<|im_start|>assistant
+```
+## How it was trained
+```ipython
+%pip install autotrain-advanced
+!autotrain setup
+!autotrain llm \
+    --train \
+    --trainer "sft" \
+    --model './TinyMistral-248M/' \
+    --model_max_length 4096 \
+    --block-size 1024 \
+    --project-name 'trained-model' \
+    --data-path "OpenAssistant/oasst_top1_2023-08-25" \
+    --train_split "train" \
+    --valid_split "test" \
+    --text-column "text" \
+    --lr 1e-5 \
+    --train_batch_size 2 \
+    --epochs 5 \
+    --evaluation_strategy "steps" \
+    --save-strategy "steps" \
+    --save-total-limit 2 \
+    --warmup-ratio 0.05 \
+    --weight-decay 0.0 \
+    --gradient-accumulation 8 \
+    --logging-steps 10 \
+    --scheduler "constant"
+```