Instructions to use djuna/Q2.5-Veltha-14B-0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use djuna/Q2.5-Veltha-14B-0.5 with Transformers:

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

pipe = pipeline("text-generation", model="djuna/Q2.5-Veltha-14B-0.5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("djuna/Q2.5-Veltha-14B-0.5")
model = AutoModelForMultimodalLM.from_pretrained("djuna/Q2.5-Veltha-14B-0.5")
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/Q2.5-Veltha-14B-0.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "djuna/Q2.5-Veltha-14B-0.5"
# 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/Q2.5-Veltha-14B-0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/djuna/Q2.5-Veltha-14B-0.5

SGLang

How to use djuna/Q2.5-Veltha-14B-0.5 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/Q2.5-Veltha-14B-0.5" \
    --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/Q2.5-Veltha-14B-0.5",
		"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/Q2.5-Veltha-14B-0.5" \
        --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/Q2.5-Veltha-14B-0.5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use djuna/Q2.5-Veltha-14B-0.5 with Docker Model Runner:
```
docker model run hf.co/djuna/Q2.5-Veltha-14B-0.5
```

djuna commited on Dec 22, 2024

Commit

d06cc2e

verified ·

1 Parent(s): db20da9

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (335ba8faeb0222299d79fe4c15151291852dd002)

Files changed (1) hide show

README.md +113 -5

README.md CHANGED Viewed

@@ -1,15 +1,109 @@
 ---
 base_model:
 - arcee-ai/SuperNova-Medius
 - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
 - allura-org/TQ2.5-14B-Aletheia-v1
 - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
 - v000000/Qwen2.5-Lumen-14B
-library_name: transformers
-tags:
-- mergekit
-- merge
 ---
 # merge
@@ -65,3 +159,17 @@ models:
       density: 0.45
 ```

 ---
+library_name: transformers
+tags:
+- mergekit
+- merge
 base_model:
 - arcee-ai/SuperNova-Medius
 - huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
 - allura-org/TQ2.5-14B-Aletheia-v1
 - EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2
 - v000000/Qwen2.5-Lumen-14B
+model-index:
+- name: Q2.5-Veltha-14B-0.5
+  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: 77.96
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 50.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 33.84
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 15.77
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 14.17
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      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: 47.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/Q2.5-Veltha-14B-0.5
+      name: Open LLM Leaderboard
 ---
 # merge
       density: 0.45
 ```
+# [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/djuna__Q2.5-Veltha-14B-0.5-details)
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |39.96|
+|IFEval (0-Shot)    |77.96|
+|BBH (3-Shot)       |50.32|
+|MATH Lvl 5 (4-Shot)|33.84|
+|GPQA (0-shot)      |15.77|
+|MuSR (0-shot)      |14.17|
+|MMLU-PRO (5-shot)  |47.72|