Instructions to use R136a1/Frostwind-10.7B-v1-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use R136a1/Frostwind-10.7B-v1-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="R136a1/Frostwind-10.7B-v1-exl2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("R136a1/Frostwind-10.7B-v1-exl2")
model = AutoModelForCausalLM.from_pretrained("R136a1/Frostwind-10.7B-v1-exl2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use R136a1/Frostwind-10.7B-v1-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "R136a1/Frostwind-10.7B-v1-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "R136a1/Frostwind-10.7B-v1-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/R136a1/Frostwind-10.7B-v1-exl2

SGLang

How to use R136a1/Frostwind-10.7B-v1-exl2 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 "R136a1/Frostwind-10.7B-v1-exl2" \
    --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": "R136a1/Frostwind-10.7B-v1-exl2",
		"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 "R136a1/Frostwind-10.7B-v1-exl2" \
        --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": "R136a1/Frostwind-10.7B-v1-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use R136a1/Frostwind-10.7B-v1-exl2 with Docker Model Runner:
```
docker model run hf.co/R136a1/Frostwind-10.7B-v1-exl2
```

8bpw 8h

Frostwind-v1

A finetune of upstage/SOLAR-10.7B-v1.0
Took Roughly 3 Hours with 4x 4090s, over 2 Epochs, with around 52K varied samples.

Dataset Composition:
20% - Coding
30% - Instruct
30% - Generalised Data
10% - Roleplay
10% - Dealignment

Testing Notes:

Fairly smart, as I expected. Obviously not at the level of the bigger models, but I did not expect that level from this.

Could be sampler issues, but generally I needed 1/2 swipes to get the correct answer when doing Zero context tests. If context is filled, no issues on my end.

For Roleplays: adding things like avoid writing as {{user}} suprisingly helps. Plus a proper prompt of course. I liked the writing style. Handles group characters in 1 card well, during my tests.

Fairly uncensored during roleplay. Yeah the as an AI stuff can happen at Zero context, but I have no issues once a character card is introduced. I had no issues making outputs that would give me 2500 Life Sentences if posted here.

Trained with Alpaca Format:

### Instruction:
<Prompt>

### Response:

### Instruction:
<Prompt>

### Input:
<Insert Context Here>

### Response:

wandb:
wandb: Run history:
wandb: eval/loss █▃▂▂▂▂▂▁▁▁▁▂▂▂▂▂▂▁▁▁
wandb: eval/runtime ▃▂▃▂▃▂▂▃▁▃█▂▃▃▃▂▃▃▂▂
wandb: eval/samples_per_second ▆▇▆▇▆▇▇▆█▆▁▇▆▆▆▇▆▆▇▇
wandb: eval/steps_per_second ▆▇▆▇▆▇▇▆█▆▁▇▆▆▆▇▆▆▇▇
wandb: train/epoch ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
wandb: train/global_step ▁▁▁▂▂▂▂▂▂▃▃▃▃▃▄▄▄▄▄▄▅▅▅▅▅▅▆▆▆▆▆▇▇▇▇▇▇███
wandb: train/learning_rate ▄███████▇▇▇▇▇▆▆▆▆▅▅▅▅▄▄▄▃▃▃▃▂▂▂▂▂▁▁▁▁▁▁▁
wandb: train/loss █▅▅▆▅▅▄▄▄▆▆▅▆▆▆▅▄▆▅▅▅▆▄▄▃▄▃▃▂▃▄▂▂▃▃▂▁▂▂▂
wandb:
wandb: Run summary:
wandb: eval/loss 0.74622
wandb: eval/runtime 72.5049
wandb: eval/samples_per_second 37.239
wandb: eval/steps_per_second 2.331
wandb: train/epoch 1.98
wandb: train/global_step 410
wandb: train/learning_rate 0.0
wandb: train/loss 0.6457
wandb: train/total_flos 3.4382652340646707e+18
wandb: train/train_loss 0.70204
wandb: train/train_runtime 10880.917
wandb: train/train_samples_per_second 9.417
wandb: train/train_steps_per_second 0.038
wandb:

Downloads last month: 3