Instructions to use Gramscii-IT/SemanticRepair-270M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gramscii-IT/SemanticRepair-270M with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Gramscii-IT/SemanticRepair-270M")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Gramscii-IT/SemanticRepair-270M 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 Gramscii-IT/SemanticRepair-270M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Gramscii-IT/SemanticRepair-270M:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Gramscii-IT/SemanticRepair-270M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Gramscii-IT/SemanticRepair-270M: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 Gramscii-IT/SemanticRepair-270M:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf Gramscii-IT/SemanticRepair-270M:Q8_0

Use Docker

docker model run hf.co/Gramscii-IT/SemanticRepair-270M:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use Gramscii-IT/SemanticRepair-270M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gramscii-IT/SemanticRepair-270M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gramscii-IT/SemanticRepair-270M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gramscii-IT/SemanticRepair-270M:Q8_0

Ollama
How to use Gramscii-IT/SemanticRepair-270M with Ollama:
```
ollama run hf.co/Gramscii-IT/SemanticRepair-270M:Q8_0
```
Unsloth Desktop

MLX LM

How to use Gramscii-IT/SemanticRepair-270M with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Gramscii-IT/SemanticRepair-270M"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Gramscii-IT/SemanticRepair-270M"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Gramscii-IT/SemanticRepair-270M",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use Gramscii-IT/SemanticRepair-270M with Docker Model Runner:
```
docker model run hf.co/Gramscii-IT/SemanticRepair-270M:Q8_0
```

Lemonade

How to use Gramscii-IT/SemanticRepair-270M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Gramscii-IT/SemanticRepair-270M:Q8_0

Run and chat with the model

lemonade run user.SemanticRepair-270M-Q8_0

List all available models

lemonade list

Atomic Chat

Gramscii commited on Aug 22

Commit

3dc78bd

verified ·

1 Parent(s): 3c1cd2b

config.json

Browse files

Files changed (1) hide show

config.json +55 -0

config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "eos_token_id": 1,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 640,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.55.2",
+    "unsloth_fixed": true,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262144
+}