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

Libraries

How to use lthn/lemrd with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lthn/lemrd",
	filename="lemrd-bf16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use lthn/lemrd with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lthn/lemrd:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lthn/lemrd:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lthn/lemrd:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lthn/lemrd:Q4_K_M

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 lthn/lemrd:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lthn/lemrd:Q4_K_M

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 lthn/lemrd:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lthn/lemrd:Q4_K_M

Use Docker

docker model run hf.co/lthn/lemrd:Q4_K_M

LM Studio
Jan

vLLM

How to use lthn/lemrd with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lthn/lemrd"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lthn/lemrd",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lthn/lemrd:Q4_K_M

Ollama
How to use lthn/lemrd with Ollama:
```
ollama run hf.co/lthn/lemrd:Q4_K_M
```

Unsloth Studio new

How to use lthn/lemrd 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 lthn/lemrd 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 lthn/lemrd to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lthn/lemrd to start chatting

Pi new

How to use lthn/lemrd with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lthn/lemrd:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "lthn/lemrd:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lthn/lemrd with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf lthn/lemrd:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default lthn/lemrd:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use lthn/lemrd with Docker Model Runner:
```
docker model run hf.co/lthn/lemrd:Q4_K_M
```

Lemonade

How to use lthn/lemrd with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lthn/lemrd:Q4_K_M

Run and chat with the model

lemonade run user.lemrd-Q4_K_M

List all available models

lemonade list

lthn commited on Apr 14

Commit

5abc300

verified ·

1 Parent(s): 78b23a6

tokenizer_config: fix response schema regex — tool_calls before content, add tool_response terminator (from google upstream 2026-04-10)

Browse files

Files changed (1) hide show

tokenizer_config.json +21 -42

tokenizer_config.json CHANGED Viewed

@@ -17,72 +17,51 @@
     "<|video|>"
   ],
   "image_token": "<|image|>",
-  "is_local": true,
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
   "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
     "properties": {
-      "content": {
-        "type": "string"
-      },
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
       "tool_calls": {
         "items": {
           "properties": {
             "function": {
               "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
                 "name": {
                   "type": "string"
                 }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
             }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
       }
     },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
   },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",

     "<|video|>"
   ],
   "image_token": "<|image|>",
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "left",
   "processor_class": "Gemma4Processor",
   "response_schema": {
+    "type": "object",
     "properties": {
       "role": {
         "const": "assistant"
       },
       "thinking": {
         "type": "string"
       },
+      "content": {
+        "type": "string"
+      },
       "tool_calls": {
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
+        "type": "array",
         "items": {
+          "type": "object",
           "properties": {
+            "type": {
+              "const": "function"
+            },
             "function": {
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
               "properties": {
                 "name": {
                   "type": "string"
+                },
+                "arguments": {
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call",
+                  "additionalProperties": {}
                 }
+              }
             }
+          }
+        }
       }
     },
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
   },
   "soc_token": "<|channel>",
   "sot_token": "<|turn>",