Instructions to use sequelbox/Llama3.1-70B-PlumChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sequelbox/Llama3.1-70B-PlumChat with Transformers:

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

pipe = pipeline("text-generation", model="sequelbox/Llama3.1-70B-PlumChat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sequelbox/Llama3.1-70B-PlumChat")
model = AutoModelForCausalLM.from_pretrained("sequelbox/Llama3.1-70B-PlumChat")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sequelbox/Llama3.1-70B-PlumChat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sequelbox/Llama3.1-70B-PlumChat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sequelbox/Llama3.1-70B-PlumChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sequelbox/Llama3.1-70B-PlumChat

SGLang

How to use sequelbox/Llama3.1-70B-PlumChat 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 "sequelbox/Llama3.1-70B-PlumChat" \
    --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": "sequelbox/Llama3.1-70B-PlumChat",
		"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 "sequelbox/Llama3.1-70B-PlumChat" \
        --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": "sequelbox/Llama3.1-70B-PlumChat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sequelbox/Llama3.1-70B-PlumChat with Docker Model Runner:
```
docker model run hf.co/sequelbox/Llama3.1-70B-PlumChat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PlumChat 70b

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

Merge Details

Shining Valiant 2 + Nemotron for high quality general chat, science-instruct, and complex query performance.

Merge Method

This model was merged using the della merge method using meta-llama/Llama-3.1-70B-Instruct as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: della
dtype: bfloat16
parameters:
  normalize: true
models:
  - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
    parameters:
      density: 0.5
      weight: 0.3
  - model: ValiantLabs/Llama3.1-70B-ShiningValiant2
    parameters:
      density: 0.5
      weight: 0.25
base_model: meta-llama/Llama-3.1-70B-Instruct

Downloads last month: 14

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for sequelbox/Llama3.1-70B-PlumChat

ValiantLabs/Llama3.1-70B-ShiningValiant2

meta-llama/Llama-3.1-70B-Instruct

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Merge model

this model

Quantizations

2 models

Evaluation results

acc on Winogrande (5-Shot)
self-reported

85.000
normalized accuracy on ARC Challenge (25-Shot)
self-reported

67.410
acc on MMLU College Biology (5-Shot)
self-reported

93.750
acc on MMLU High School Biology (5-Shot)
self-reported

91.940
acc on MMLU Conceptual Physics (5-Shot)
self-reported

82.130
acc on MMLU College Physics (5-Shot)
self-reported

60.780
acc on MMLU High School Physics (5-Shot)
self-reported

62.250
acc on MMLU College Chemistry (5-Shot)
self-reported

56.000
acc on MMLU High School Chemistry (5-Shot)
self-reported

73.400
acc on MMLU Astronomy (5-Shot)
self-reported

89.470
acc on MMLU College Computer Science (5-Shot)
self-reported

64.000
acc on MMLU High School Computer Science (5-Shot)
self-reported

90.000
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

56.160
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

52.810
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

29.980
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

18.790