Instructions to use icefog72/IceEspressoRPv2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use icefog72/IceEspressoRPv2-7b with Transformers:

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

pipe = pipeline("text-generation", model="icefog72/IceEspressoRPv2-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("icefog72/IceEspressoRPv2-7b")
model = AutoModelForCausalLM.from_pretrained("icefog72/IceEspressoRPv2-7b")
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 icefog72/IceEspressoRPv2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "icefog72/IceEspressoRPv2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "icefog72/IceEspressoRPv2-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/icefog72/IceEspressoRPv2-7b

SGLang

How to use icefog72/IceEspressoRPv2-7b 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 "icefog72/IceEspressoRPv2-7b" \
    --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": "icefog72/IceEspressoRPv2-7b",
		"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 "icefog72/IceEspressoRPv2-7b" \
        --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": "icefog72/IceEspressoRPv2-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use icefog72/IceEspressoRPv2-7b with Docker Model Runner:
```
docker model run hf.co/icefog72/IceEspressoRPv2-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

IceEspressoRPv2-7b

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

G:\FModels\IceTea21EnergyDrinkRPV13-DPOv4-bin
G:\FModels\IceEspressoRPv1-7b-dpo-bin

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: G:\FModels\IceTea21EnergyDrinkRPV13-DPOv4-bin
        layer_range: [0, 32]
      - model: G:\FModels\IceEspressoRPv1-7b-dpo-bin
        layer_range: [0, 32]

merge_method: slerp
base_model: G:\FModels\IceEspressoRPv1-7b-dpo-bin
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors

dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.25
IFEval (0-Shot)	49.77
BBH (3-Shot)	31.30
MATH Lvl 5 (4-Shot)	5.51
GPQA (0-shot)	5.26
MuSR (0-shot)	12.77
MMLU-PRO (5-shot)	22.90

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for icefog72/IceEspressoRPv2-7b

Quantizations

2 models

Evaluation results

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

49.770
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

31.300
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

5.510
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

5.260
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

12.770
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

22.900