Not-For-All-Audiences

Instructions to use bamec66557/VICIOUS_MESH-12B-BETA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bamec66557/VICIOUS_MESH-12B-BETA with Transformers:

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

pipe = pipeline("text-generation", model="bamec66557/VICIOUS_MESH-12B-BETA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bamec66557/VICIOUS_MESH-12B-BETA")
model = AutoModelForCausalLM.from_pretrained("bamec66557/VICIOUS_MESH-12B-BETA", device_map="auto")
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 bamec66557/VICIOUS_MESH-12B-BETA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bamec66557/VICIOUS_MESH-12B-BETA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bamec66557/VICIOUS_MESH-12B-BETA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bamec66557/VICIOUS_MESH-12B-BETA

SGLang

How to use bamec66557/VICIOUS_MESH-12B-BETA 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 "bamec66557/VICIOUS_MESH-12B-BETA" \
    --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": "bamec66557/VICIOUS_MESH-12B-BETA",
		"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 "bamec66557/VICIOUS_MESH-12B-BETA" \
        --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": "bamec66557/VICIOUS_MESH-12B-BETA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bamec66557/VICIOUS_MESH-12B-BETA with Docker Model Runner:
```
docker model run hf.co/bamec66557/VICIOUS_MESH-12B-BETA
```

bamec66557 commited on Dec 20, 2024

Commit

2aabca0

verified ·

1 Parent(s): 624dd4b

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -8

README.md CHANGED Viewed

@@ -4,6 +4,7 @@ library_name: transformers
 tags:
 - mergekit
 - merge
 base_model:
 - bamec66557/VICIOUS_MESH-12B-ALPHA
 - Infermatic/MN-12B-Inferor-v0.1
@@ -24,7 +25,8 @@ model-index:
       value: 67.21
       name: strict accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -39,7 +41,8 @@ model-index:
       value: 31.36
       name: normalized accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -54,7 +57,8 @@ model-index:
       value: 12.08
       name: exact match
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -69,7 +73,8 @@ model-index:
       value: 8.84
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -84,7 +89,8 @@ model-index:
       value: 14.34
       name: acc_norm
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
@@ -101,8 +107,19 @@ model-index:
       value: 29.76
       name: accuracy
     source:
-      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
 ---
 # merge
@@ -154,5 +171,4 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 |MATH Lvl 5 (4-Shot)|12.08|
 |GPQA (0-shot)      | 8.84|
 |MuSR (0-shot)      |14.34|
-|MMLU-PRO (5-shot)  |29.76|

 tags:
 - mergekit
 - merge
+- not-for-all-audiences
 base_model:
 - bamec66557/VICIOUS_MESH-12B-ALPHA
 - Infermatic/MN-12B-Inferor-v0.1
       value: 67.21
       name: strict accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 31.36
       name: normalized accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 12.08
       name: exact match
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 8.84
       name: acc_norm
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 14.34
       name: acc_norm
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
   - task:
       type: text-generation
       value: 29.76
       name: accuracy
     source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bamec66557/VICIOUS_MESH-12B-BETA
       name: Open LLM Leaderboard
+datasets:
+- open-llm-leaderboard/bamec66557__VICIOUS_MESH-12B-BETA-details
+- open-llm-leaderboard/bamec66557__VICIOUS_MESH-12B-ALPHA-details
+language:
+- en
+- ja
+- ru
+- zh
+- ko
+- es
 ---
 # merge
 |MATH Lvl 5 (4-Shot)|12.08|
 |GPQA (0-shot)      | 8.84|
 |MuSR (0-shot)      |14.34|
+|MMLU-PRO (5-shot)  |29.76|