Instructions to use djuna/L3.1-ForStHS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use djuna/L3.1-ForStHS with Transformers:

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

pipe = pipeline("text-generation", model="djuna/L3.1-ForStHS")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("djuna/L3.1-ForStHS")
model = AutoModelForCausalLM.from_pretrained("djuna/L3.1-ForStHS")
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 djuna/L3.1-ForStHS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "djuna/L3.1-ForStHS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "djuna/L3.1-ForStHS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/djuna/L3.1-ForStHS

SGLang

How to use djuna/L3.1-ForStHS 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 "djuna/L3.1-ForStHS" \
    --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": "djuna/L3.1-ForStHS",
		"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 "djuna/L3.1-ForStHS" \
        --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": "djuna/L3.1-ForStHS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use djuna/L3.1-ForStHS with Docker Model Runner:
```
docker model run hf.co/djuna/L3.1-ForStHS
```

L3.1-ForStHS / README.md

djuna

Adding Evaluation Results (#2)

305aa17 verified over 1 year ago

preview code

raw

history blame contribute delete

4.54 kB

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - rityak/L3.1-FormaxGradient
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
  - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - DreadPoor/Heart_Stolen-8B-Model_Stock
model-index:
  - name: L3.1-ForStHS
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 78.13
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 31.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 12.92
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 5.48
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 9.66
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 30.39
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-ForStHS
          name: Open LLM Leaderboard

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using vicgalle/Configurable-Llama-3.1-8B-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:

models:
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
  - model: rityak/L3.1-FormaxGradient
merge_method: model_stock
base_model: vicgalle/Configurable-Llama-3.1-8B-Instruct
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.00
IFEval (0-Shot)	78.13
BBH (3-Shot)	31.39
MATH Lvl 5 (4-Shot)	12.92
GPQA (0-shot)	5.48
MuSR (0-shot)	9.66
MMLU-PRO (5-shot)	30.39