Instructions to use Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2")
model = AutoModelForCausalLM.from_pretrained("Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2

SGLang

How to use Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2 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 "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2 with Docker Model Runner:
```
docker model run hf.co/Pretergeek/openchat-3.5-0106_Rebased_Mistral-7B-v0.2
```

This model was created as an experiment on using LoRA extraction to replicate Openchat-3.5-0106 using Mistral-7B-v0.2 as a base model instead of the original Mistral-7B-v0.1.

Openchat-3.5-0106 is an excellent model but was based on Mistral-7B-v0.1 which has a context window of 8192 tokens. Mistral-7B-v0.2 has a context window of 32768 tokens. I could have extended OpenChat-3.5 context myself with RoPE and/or YaRN but that has been done. There are many models on HF that have done exactly that. Instead I decided to try and replicate OpenChat-3.5-0106 using the LoRA extraction method available in mergekit. These are the steps I followed:

Extract a LoRA with rank 512 from OpenChat-3.5-0106 using One's Mistral_7B_with_EOT_token as the base model.
Replicate imone's work by adding the EOT token to Mistral-7B-v0.2, creating Mistral-7B-v0.2_EOT.
Merge the LoRA's weights to the Mistral-7B-v0.2_EOT model.

This is the result. This model is not meant for use, it was created to test if this method is viable for replacing the base model of fine-tuned models (when tokenizer and weights have not been changed too much). I am uploading here for evaluation. I don't expect this model to match the original OpenChat-3.5-0106 since I used a LoRA with rank 512, so it won't be equivalent to a full fine-tuning. I have been able to extract LoRAs with higher rank, but currently I don't have the resources to merge them with the model as the memory requirements exceed what I have at my disposal. If you would like to help my work, check my Ko-Fi and/or Patreon:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	15.94
IFEval (0-Shot)	37.06
BBH (3-Shot)	10.91
MATH Lvl 5 (4-Shot)	3.85
GPQA (0-shot)	2.91
MuSR (0-shot)	20.57
MMLU-PRO (5-shot)	20.33

Downloads last month: 20

Safetensors

Model size

7B params

Tensor type

BF16

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

37.060
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

10.910
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

3.850
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

2.910
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

20.570
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

20.330