Instructions to use NagusameCS/minSode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NagusameCS/minSode with Transformers:

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

pipe = pipeline("text-generation", model="NagusameCS/minSode")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NagusameCS/minSode")
model = AutoModelForCausalLM.from_pretrained("NagusameCS/minSode", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use NagusameCS/minSode with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NagusameCS/minSode:Q8_0
# Run inference directly in the terminal:
llama cli -hf NagusameCS/minSode:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NagusameCS/minSode:Q8_0
# Run inference directly in the terminal:
llama cli -hf NagusameCS/minSode:Q8_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf NagusameCS/minSode:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf NagusameCS/minSode:Q8_0

Use Docker

docker model run hf.co/NagusameCS/minSode:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use NagusameCS/minSode with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NagusameCS/minSode:Q8_0

SGLang

How to use NagusameCS/minSode 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 "NagusameCS/minSode" \
    --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": "NagusameCS/minSode",
		"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 "NagusameCS/minSode" \
        --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": "NagusameCS/minSode",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use NagusameCS/minSode with Ollama:
```
ollama run hf.co/NagusameCS/minSode:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use NagusameCS/minSode with Docker Model Runner:
```
docker model run hf.co/NagusameCS/minSode:Q8_0
```

Lemonade

How to use NagusameCS/minSode with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NagusameCS/minSode:Q8_0

Run and chat with the model

lemonade run user.minSode-Q8_0

List all available models

lemonade list

Atomic Chat

minSode / README.md

NagusameCS

Fix packaging (transformers 4.x tokenizer/RoPE, tokenizer truncation, license, base_model) and correct the model card with measured quality (audit 2026-10-09); add Q8_0 GGUF and a working Ollama Modelfile

9e17c17 verified about 1 month ago

preview code

Raw History Blame Contribute Delete

2.95 kB

---
language: en
license: apache-2.0
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
library_name: transformers
pipeline_tag: text-generation
tags:
- hypertensor
- ceci-graft
- smollm2
- experimental
---
# minSode (minSøde): "my sweet"

An experimental weight-surgery variant of [SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct),
made with the HyperTensor CECI "graft" procedure. It is a research artifact: it does **not** outperform its base model.

## What was changed

Only the layer-5 MLP (`gate_proj`, `up_proj`, `down_proj`) was changed: `W5 <- W5 + 0.5 * (W15 - W5) @ P` (`P @ (...)` for `down_proj`), where `P` projects onto the top-230 right-singular vectors of layer 5's `q_proj`. Created by `scripts/graft_proof.py` ("Kimære").

The other 269 of 272 tensors are bit-identical to the base model. Weights are stored in float32. The tokenizer and chat template are the base model's.

## Measured quality (audit, 2026-10-09)

Teacher-forced next-token loss on 30 web and 30 code documents (512 tokens each, `data/corpus/{web,code}.dev.jsonl`), compared with the base model:

| text | base NLL | this model NLL | perplexity change | top-1 agreement with base | KL(base‖model) |
|---|---|---|---|---|---|
| web | 2.865 | 2.896 | +3.1% | 89.6% | 0.044 |
| code | 1.783 | 1.838 | +5.6% | 90.9% | 0.063 |
| all | 2.324 | 2.367 | +4.3% | 90.3% | 0.053 |

| original HyperTensor test | base | this model |
|---|---|---|
| graft_proof 15-sentence PPL (mean of per-sentence PPL) | 60.96 | 60.68 |
| graft_benchmark MMLU-lite (50 items) | 31/50 | 32/50 (+1 / -0 items, sign-test p=1.00) |
| graft_benchmark BoolQ (15 items) | 6/15 | 4/15 (+1 / -3, p=0.62) |
The earlier card claimed "105% PPL recovery, outperforms original". The "% recovery" figures compared this model with a copy of the base whose MLP had been zeroed.
This model was never ablated, so they do not measure recovery. On real text the model is slightly worse than its base, and the small
MMLU-lite/BoolQ differences are a few items out of 50/15 and are not statistically significant.
## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("NagusameCS/minSode")
model = AutoModelForCausalLM.from_pretrained("NagusameCS/minSode")
msgs = [{"role": "user", "content": "What is the capital of France?"}]
inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)
out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
```
### Ollama
The repo includes `minSode-Q8_0.gguf` and a `Modelfile`:
```bash
hf download NagusameCS/minSode --local-dir minSode && cd minSode
ollama create minsode -f Modelfile && ollama run minsode
# or directly: ollama run hf.co/NagusameCS/minSode
```
Source: [HyperTensor](https://github.com/NagusameCS/HyperTensor).

	---
	language: en
	license: apache-2.0
	base_model: HuggingFaceTB/SmolLM2-135M-Instruct
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- hypertensor
	- ceci-graft
	- smollm2
	- experimental
	---

	# minSode (minSøde): "my sweet"

	An experimental weight-surgery variant of [SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct),
	made with the HyperTensor CECI "graft" procedure. It is a research artifact: it does not outperform its base model.

	## What was changed

	Only the layer-5 MLP (`gate_proj`, `up_proj`, `down_proj`) was changed: `W5 <- W5 + 0.5 * (W15 - W5) @ P` (`P @ (...)` for `down_proj`), where `P` projects onto the top-230 right-singular vectors of layer 5's `q_proj`. Created by `scripts/graft_proof.py` ("Kimære").

	The other 269 of 272 tensors are bit-identical to the base model. Weights are stored in float32. The tokenizer and chat template are the base model's.

	## Measured quality (audit, 2026-10-09)

	Teacher-forced next-token loss on 30 web and 30 code documents (512 tokens each, `data/corpus/{web,code}.dev.jsonl`), compared with the base model:

	\| text \| base NLL \| this model NLL \| perplexity change \| top-1 agreement with base \| KL(base‖model) \|
	\|---\|---\|---\|---\|---\|---\|
	\| web \| 2.865 \| 2.896 \| +3.1% \| 89.6% \| 0.044 \|
	\| code \| 1.783 \| 1.838 \| +5.6% \| 90.9% \| 0.063 \|
	\| all \| 2.324 \| 2.367 \| +4.3% \| 90.3% \| 0.053 \|

	\| original HyperTensor test \| base \| this model \|
	\|---\|---\|---\|
	\| graft_proof 15-sentence PPL (mean of per-sentence PPL) \| 60.96 \| 60.68 \|
	\| graft_benchmark MMLU-lite (50 items) \| 31/50 \| 32/50 (+1 / -0 items, sign-test p=1.00) \|
	\| graft_benchmark BoolQ (15 items) \| 6/15 \| 4/15 (+1 / -3, p=0.62) \|

	The earlier card claimed "105% PPL recovery, outperforms original". The "% recovery" figures compared this model with a copy of the base whose MLP had been zeroed.
	This model was never ablated, so they do not measure recovery. On real text the model is slightly worse than its base, and the small
	MMLU-lite/BoolQ differences are a few items out of 50/15 and are not statistically significant.

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	tok = AutoTokenizer.from_pretrained("NagusameCS/minSode")
	model = AutoModelForCausalLM.from_pretrained("NagusameCS/minSode")
	msgs = [{"role": "user", "content": "What is the capital of France?"}]
	inputs = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt", return_dict=True)
	out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
	print(tok.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
	```

	### Ollama

	The repo includes `minSode-Q8_0.gguf` and a `Modelfile`:

	```bash
	hf download NagusameCS/minSode --local-dir minSode && cd minSode
	ollama create minsode -f Modelfile && ollama run minsode
	# or directly: ollama run hf.co/NagusameCS/minSode
	```

	Source: [HyperTensor](https://github.com/NagusameCS/HyperTensor).