Instructions to use Nitral-Archive/Prima-Pastacles-7b-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitral-Archive/Prima-Pastacles-7b-128k with Transformers:

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

pipe = pipeline("text-generation", model="Nitral-Archive/Prima-Pastacles-7b-128k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nitral-Archive/Prima-Pastacles-7b-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Nitral-Archive/Prima-Pastacles-7b-128k", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nitral-Archive/Prima-Pastacles-7b-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nitral-Archive/Prima-Pastacles-7b-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nitral-Archive/Prima-Pastacles-7b-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Nitral-Archive/Prima-Pastacles-7b-128k

SGLang

How to use Nitral-Archive/Prima-Pastacles-7b-128k 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 "Nitral-Archive/Prima-Pastacles-7b-128k" \
    --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": "Nitral-Archive/Prima-Pastacles-7b-128k",
		"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 "Nitral-Archive/Prima-Pastacles-7b-128k" \
        --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": "Nitral-Archive/Prima-Pastacles-7b-128k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nitral-Archive/Prima-Pastacles-7b-128k with Docker Model Runner:
```
docker model run hf.co/Nitral-Archive/Prima-Pastacles-7b-128k
```

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Test157t/Prima-Pastacles-7b
        layer_range: [0, 32]
      - model: Test157t/Pasta-Sea-7b-128k
        layer_range: [0, 32]
merge_method: slerp
base_model: Test157t/Prima-Pastacles-7b
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
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.36
AI2 Reasoning Challenge (25-Shot)	68.09
HellaSwag (10-Shot)	86.57
MMLU (5-Shot)	64.58
TruthfulQA (0-shot)	62.51
Winogrande (5-shot)	81.06
GSM8k (5-shot)	59.36

Downloads last month: 38

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Nitral-Archive/Prima-Pastacles-7b-128k

Base model

Nitral-Archive/Prima-Pastacles-7b

Finetuned

(1)

this model

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

68.090
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.570
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.580
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

62.510
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

81.060
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

59.360