Instructions to use Scorched2/shader-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Scorched2/shader-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Scorched2/shader-v2")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Scorched2/shader-v2", dtype="auto")

llama-cpp-python

How to use Scorched2/shader-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Scorched2/shader-v2",
	filename="hrm-350m-q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Scorched2/shader-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Scorched2/shader-v2:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Scorched2/shader-v2:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Scorched2/shader-v2:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Scorched2/shader-v2:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Scorched2/shader-v2:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Scorched2/shader-v2:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Scorched2/shader-v2:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Scorched2/shader-v2:Q8_0

Use Docker

docker model run hf.co/Scorched2/shader-v2:Q8_0

LM Studio
Jan

vLLM

How to use Scorched2/shader-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Scorched2/shader-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Scorched2/shader-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Scorched2/shader-v2:Q8_0

SGLang

How to use Scorched2/shader-v2 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 "Scorched2/shader-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Scorched2/shader-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Scorched2/shader-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Scorched2/shader-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Scorched2/shader-v2 with Ollama:
```
ollama run hf.co/Scorched2/shader-v2:Q8_0
```

Unsloth Studio

How to use Scorched2/shader-v2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Scorched2/shader-v2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Scorched2/shader-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Scorched2/shader-v2 to start chatting

Docker Model Runner
How to use Scorched2/shader-v2 with Docker Model Runner:
```
docker model run hf.co/Scorched2/shader-v2:Q8_0
```

Lemonade

How to use Scorched2/shader-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Scorched2/shader-v2:Q8_0

Run and chat with the model

lemonade run user.shader-v2-Q8_0

List all available models

lemonade list

Scorched2 commited on May 3

Commit

3a62af9

verified ·

1 Parent(s): 461f4de

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

README.md +25 -0
config.json +37 -0
generation_config.json +9 -0
model.safetensors +3 -0
tokenizer.json +0 -0
tokenizer_config.json +13 -0

README.md ADDED Viewed

	@@ -0,0 +1,25 @@

+---
+library_name: transformers
+tags: [hrm, moe, hierarchical-reasoning, custom-architecture]
+---
+# Hierarchical Reasoning Model (HRM)
+Custom MoE language model with 3-level hierarchical reasoning and DeepSeek-V3 memory strategies.
+**Architecture:** 3 levels · 16 experts (4 active) · MLA attention · Hierarchical memory
+**Parameters:** ~350M total, ~45M active per token
+**Trained on:** OpenHermes-2.5
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("Scorched2/shader-v2", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("Scorched2/shader-v2")
+inputs = tokenizer("### Instruction:\nExplain AI.\n\n### Response:\n", return_tensors="pt")
+out = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(out[0]))
+```

config.json ADDED Viewed

	@@ -0,0 +1,37 @@

+{
+  "architectures": [
+    "HRMForCausalLM"
+  ],
+  "bos_token_id": 50256,
+  "d_ff": 1536,
+  "d_model": 768,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 50256,
+  "episodic_mem_slots": 64,
+  "head_dim": 64,
+  "kv_lora_rank": 192,
+  "layers_per_level": [
+    3,
+    3,
+    3
+  ],
+  "max_seq_len": 256,
+  "model_type": "hrm",
+  "moe_d_ff": 512,
+  "mtp_heads": 2,
+  "n_active_experts": 4,
+  "n_experts": 16,
+  "n_heads": 12,
+  "n_levels": 3,
+  "n_shared_experts": 1,
+  "pad_token_id": 0,
+  "q_lora_rank": 256,
+  "rope_head_dim": 32,
+  "semantic_mem_dim": 768,
+  "semantic_mem_size": 512,
+  "tie_embeddings": true,
+  "transformers_version": "5.7.0",
+  "vocab_size": 50257,
+  "working_mem_slots": 16
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.7.0"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7854934776f17859694a4f26ae0bcf329f9c6ccf3f932ee16ae6bb45878101
+size 1301867064

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}