Instructions to use sometimesanotion/Lamarck-14B-v0.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sometimesanotion/Lamarck-14B-v0.7 with Transformers:

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

pipe = pipeline("text-generation", model="sometimesanotion/Lamarck-14B-v0.7")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sometimesanotion/Lamarck-14B-v0.7")
model = AutoModelForCausalLM.from_pretrained("sometimesanotion/Lamarck-14B-v0.7", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sometimesanotion/Lamarck-14B-v0.7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sometimesanotion/Lamarck-14B-v0.7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sometimesanotion/Lamarck-14B-v0.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sometimesanotion/Lamarck-14B-v0.7

SGLang

How to use sometimesanotion/Lamarck-14B-v0.7 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 "sometimesanotion/Lamarck-14B-v0.7" \
    --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": "sometimesanotion/Lamarck-14B-v0.7",
		"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 "sometimesanotion/Lamarck-14B-v0.7" \
        --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": "sometimesanotion/Lamarck-14B-v0.7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sometimesanotion/Lamarck-14B-v0.7 with Docker Model Runner:
```
docker model run hf.co/sometimesanotion/Lamarck-14B-v0.7
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

With no benchmark regressions, mostly gains over the previous release, this version of Lamarck has broken the 41.0 average maximum for 14B parameter models. Those providing feedback, thank you!

Lamarck 14B v0.7: A generalist merge with emphasis on multi-step reasoning, prose, and multi-language ability. The 14B parameter model class has a lot of strong performers, and Lamarck strives to be well-rounded and solid:

Lamarck is produced by a custom toolchain to automate a process of LoRAs and layer-targeting merges:

Extracted LoRA adapters from special-purpose merges
Custom base models and model_stocks, with LoRAs from from huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 to minimize IFEVAL loss often seen in model_stock merges
Separate branches for aggressive breadcrumbs and conservative DELLA merges
Highly targeted weight/density gradients for every 2-4 layers, at each stage
Finalization through SLERP+TIES merges recombining the breadcrumbs and DELLA branches to taste

Lamarck's performance comes from an ancestry that goes back through careful merges to select finetuning work, upcycled and combined. Through intermediate merges, arcee-ai/Virtuoso-Small sthenno-com/miscii-14b-1225 and VAGOsolutions/SauerkrautLM-v2-14b-DPO are emphasized in early layers for extra BBH; later layers add synergistic influence from deepseek-ai/DeepSeek-R1-Distill-Qwen-14B, Krystalan/DRT-o1-14B, EVA-UNIT-01/EVA-Qwen2.5-14B-v0.2, and CultriX/Qwen2.5-14B-Wernicke.

More subjectively, its prose and translation abilities are boosted by repeated re-emphasis of Krystalan/DRT-o1-14B and underwoods/medius-erebus-magnum-14b. Other models found in sometimesanotion/Qwenvergence-14B-v3-Prose have their impact on prose quality - and surprising synergy of reasoning.

Kudos to @arcee-ai, @deepseek-ai, @Krystalan, @underwoods, @VAGOSolutions, @CultriX, @sthenno-com, and @rombodawg whose models had the most influence. Vimarckoso v3 has the model card which documents its extended lineage.

Downloads last month: 1,476

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for sometimesanotion/Lamarck-14B-v0.7

arcee-ai/Virtuoso-Small

deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

sometimesanotion/Lamarck-14B-v0.3

sometimesanotion/Lamarck-14B-v0.6

Merge model

this model

Finetunes

3 models

Merges

20 models

Quantizations

10 models

Spaces using sometimesanotion/Lamarck-14B-v0.7 17

Collection including sometimesanotion/Lamarck-14B-v0.7

Lamarck-14B Qwen 2.5 and relatives

Collection

Lamarck's public releases, plus significant related merges and finetunes • 6 items • Updated Feb 18, 2025 • 1