Instructions to use Naphula/Salamander-24B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Salamander-24B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Naphula/Salamander-24B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Salamander-24B-v1")
model = AutoModelForMultimodalLM.from_pretrained("Naphula/Salamander-24B-v1")
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 Naphula/Salamander-24B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Salamander-24B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Salamander-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Salamander-24B-v1

SGLang

How to use Naphula/Salamander-24B-v1 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 "Naphula/Salamander-24B-v1" \
    --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": "Naphula/Salamander-24B-v1",
		"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 "Naphula/Salamander-24B-v1" \
        --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": "Naphula/Salamander-24B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Salamander-24B-v1 with Docker Model Runner:
```
docker model run hf.co/Naphula/Salamander-24B-v1
```

Naphula commited on May 2

Commit

e6ea92a

verified ·

1 Parent(s): 5f0bc46

Update README.md

Browse files

Files changed (1) hide show

README.md +37 -0

README.md CHANGED Viewed

@@ -1,3 +1,40 @@
 new `della` merge combining several 2501, 2506, and 2509 models, with fallen mistral 2503 also sprinkled in.
 needs more testing, but no refusals so far

+---
+base_model:
+- Darkhn/Magistral-2509-24B-Text-Only
+- ReadyArt/Broken-Tutu-24B-Transgression-v2.0
+- MuXodious/Tiamat-24B-Magistral-PaperWitch-heresy
+- llmfan46/MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1
+- ReadyArt/Dark-Nexus-24B-v2.0
+- ReadyArt/4.2.0-Broken-Tutu-24b
+- Undi95/MistralThinker-v1.1
+- TheDrummer/Magidonia-24B-v4.3
+- TheDrummer/Rivermind-24B-v1
+- MuXodious/Hearthfire-24B-absolute-heresy
+- Darkhn/M3.2-24B-Animus-V7.1
+- zerofata/MS3.2-PaintedFantasy-v3-24B
+- CrucibleLab/M3.2-24B-Loki-V1.3
+- aixonlab/Eurydice-24b-v3.5
+- Nabbers1999/MS-24B-Bathory-GRPO
+- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
+- allura-forge/ms32-final-TEXTONLY
+- TheDrummer/Precog-24B-v1
+- dphn/Dolphin-Mistral-24B-Venice-Edition
+- TroyDoesAI/BlackSheep-24B
+- trashpanda-org/MS3.2-24B-Mullein-v2
+- TheDrummer/Cydonia-24B-v4.3
+- zerofata/MS3.2-PaintedFantasy-v2-24B
+language: eng
+library_name: transformers
+license: apache-2.0
+tags:
+- mergekit
+- merge
+- mistral
+- della
+---
+# Checkpoint 82
 new `della` merge combining several 2501, 2506, and 2509 models, with fallen mistral 2503 also sprinkled in.
 needs more testing, but no refusals so far