Instructions to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="leafspark/Llama-3.1-8B-MultiReflection-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leafspark/Llama-3.1-8B-MultiReflection-Instruct")
model = AutoModelForCausalLM.from_pretrained("leafspark/Llama-3.1-8B-MultiReflection-Instruct")
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]:]))

PEFT
How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with PEFT:
```
Task type is invalid.
```
Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leafspark/Llama-3.1-8B-MultiReflection-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leafspark/Llama-3.1-8B-MultiReflection-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct

SGLang

How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct 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 "leafspark/Llama-3.1-8B-MultiReflection-Instruct" \
    --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": "leafspark/Llama-3.1-8B-MultiReflection-Instruct",
		"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 "leafspark/Llama-3.1-8B-MultiReflection-Instruct" \
        --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": "leafspark/Llama-3.1-8B-MultiReflection-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leafspark/Llama-3.1-8B-MultiReflection-Instruct to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for leafspark/Llama-3.1-8B-MultiReflection-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for leafspark/Llama-3.1-8B-MultiReflection-Instruct to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="leafspark/Llama-3.1-8B-MultiReflection-Instruct",
    max_seq_length=2048,
)

Docker Model Runner
How to use leafspark/Llama-3.1-8B-MultiReflection-Instruct with Docker Model Runner:
```
docker model run hf.co/leafspark/Llama-3.1-8B-MultiReflection-Instruct
```

leafspark

leaderboard-pr-bot commited on Sep 16, 2024

Commit

a355780

verified ·

1 Parent(s): 7e381ea

Adding Evaluation Results (#1)

Browse files

- Adding Evaluation Results (851556518c302703c1b142bd4c482480b5089d36)

Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +113 -4

README.md CHANGED Viewed

@@ -1,8 +1,4 @@
 ---
-license: llama3.1
-base_model:
-- meta-llama/Meta-Llama-3.1-8B-Instruct
-library_name: transformers
 language:
 - en
 - de
@@ -12,16 +8,115 @@ language:
 - hi
 - es
 - th
 tags:
 - reflection
 - unsloth
 - peft
 - llama
 datasets:
 - leafspark/DetailedReflection-Claude-v3_5-Sonnet
 metrics:
 - accuracy
 pipeline_tag: text-generation
 ---
 # Llama-3.1-8B-MultiReflection-Instruct
@@ -292,3 +387,17 @@ Now, it's your turn again. Can you think of any real-world applications of this
 Remember, this is a proof, not a mathematical exercise. Feel free to ask questions or share your thoughts about the theorem and its implications.
 </output>
 ```

 ---
 language:
 - en
 - de
 - hi
 - es
 - th
+license: llama3.1
+library_name: transformers
 tags:
 - reflection
 - unsloth
 - peft
 - llama
+base_model:
+- meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
 - leafspark/DetailedReflection-Claude-v3_5-Sonnet
 metrics:
 - accuracy
 pipeline_tag: text-generation
+model-index:
+- name: Llama-3.1-8B-MultiReflection-Instruct
+  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: 71.25
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      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: 28.45
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      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: 12.54
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      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: 5.7
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      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: 8.52
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      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: 30.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=leafspark/Llama-3.1-8B-MultiReflection-Instruct
+      name: Open LLM Leaderboard
 ---
 # Llama-3.1-8B-MultiReflection-Instruct
 Remember, this is a proof, not a mathematical exercise. Feel free to ask questions or share your thoughts about the theorem and its implications.
 </output>
 ```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_leafspark__Llama-3.1-8B-MultiReflection-Instruct)
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |26.12|
+|IFEval (0-Shot)    |71.25|
+|BBH (3-Shot)       |28.45|
+|MATH Lvl 5 (4-Shot)|12.54|
+|GPQA (0-shot)      | 5.70|
+|MuSR (0-shot)      | 8.52|
+|MMLU-PRO (5-shot)  |30.27|