Instructions to use dr-housemd/Salamander-24B-v1-exl3-3.50bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dr-housemd/Salamander-24B-v1-exl3-3.50bpw with Transformers:

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

pipe = pipeline("text-generation", model="dr-housemd/Salamander-24B-v1-exl3-3.50bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dr-housemd/Salamander-24B-v1-exl3-3.50bpw")
model = AutoModelForCausalLM.from_pretrained("dr-housemd/Salamander-24B-v1-exl3-3.50bpw")
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

vLLM

How to use dr-housemd/Salamander-24B-v1-exl3-3.50bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dr-housemd/Salamander-24B-v1-exl3-3.50bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dr-housemd/Salamander-24B-v1-exl3-3.50bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dr-housemd/Salamander-24B-v1-exl3-3.50bpw

SGLang

How to use dr-housemd/Salamander-24B-v1-exl3-3.50bpw 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 "dr-housemd/Salamander-24B-v1-exl3-3.50bpw" \
    --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": "dr-housemd/Salamander-24B-v1-exl3-3.50bpw",
		"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 "dr-housemd/Salamander-24B-v1-exl3-3.50bpw" \
        --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": "dr-housemd/Salamander-24B-v1-exl3-3.50bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dr-housemd/Salamander-24B-v1-exl3-3.50bpw with Docker Model Runner:
```
docker model run hf.co/dr-housemd/Salamander-24B-v1-exl3-3.50bpw
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

3.50bpw exl3 quant. 8 head bits.

Model's Card:

Salamander 24B v1

This is Checkpoint 82, a new della merge combining several 2501, 2506, and 2509 models, with fallen mistral 2503 also sprinkled in.

No refusals were observed in the initial tests. The model should not require ablation or jailbreaks.

architecture: MistralForCausalLM
models:
  ## BASE ##
  - model: B:\24B\Darkhn--Magistral-2509-24B-Text-Only
  ## 2501 ##
  - model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09 
  - model: B:\24B\PrivateMerge29 # This merge is no longer available on HF
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--Nabbers1999--MS-24B-Bathory-GRPO
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--dphn--Dolphin-Mistral-24B-Venice-Edition
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--TroyDoesAI--BlackSheep-24B
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--aixonlab--Eurydice-24b-v3.5
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--Undi95--MistralThinker-v1.1
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09 
  ## 2503 ##
  - model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  ## 2506 ##
  - model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
    parameters:
      weight: 0.1
      weight: 0.09
      epsilon: 0.09    
  - model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--TheDrummer--Rivermind-24B-v1
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--allura-forge--ms32-final-TEXTONLY
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V1.3
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\MuXodious--Hearthfire-24B-absolute-heresy
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--ReadyArt--Dark-Nexus-24B-v2.0
    parameters:
      weight: 0.1
      density: 0.9
      epsilon: 0.09    
  ## 2509##
  - model: B:\24B\!models--TheDrummer--Precog-24B-v1
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\llmfan46--MS3.2-PaintedFantasy-v4.1-24B-ultra-uncensored-heretic-v1
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\24B\MuXodious--Tiamat-24B-Magistral-PaperWitch-heresy\textonly
    parameters:
      weight: 0.2
      density: 0.9
      epsilon: 0.09
merge_method: della
base_model: B:\24B\Darkhn--Magistral-2509-24B-Text-Only
parameters:
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
tokenizer:
  source: union
dtype: float32
out_dtype: bfloat16
name: C82