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

Libraries

How to use lolilolikon/ai_knowledge with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lolilolikon/ai_knowledge",
	filename="deepseek-r1-distill-qwen-1.5b.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lolilolikon/ai_knowledge 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 lolilolikon/ai_knowledge:Q8_0
# Run inference directly in the terminal:
llama cli -hf lolilolikon/ai_knowledge:Q8_0

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/lolilolikon/ai_knowledge:Q8_0

LM Studio
Jan
Ollama
How to use lolilolikon/ai_knowledge with Ollama:
```
ollama run hf.co/lolilolikon/ai_knowledge:Q8_0
```

Unsloth Studio

How to use lolilolikon/ai_knowledge 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 lolilolikon/ai_knowledge 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 lolilolikon/ai_knowledge to start chatting

Using HuggingFace Spaces for Unsloth

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

Atomic Chat new
Docker Model Runner
How to use lolilolikon/ai_knowledge with Docker Model Runner:
```
docker model run hf.co/lolilolikon/ai_knowledge:Q8_0
```

Lemonade

How to use lolilolikon/ai_knowledge with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lolilolikon/ai_knowledge:Q8_0

Run and chat with the model

lemonade run user.ai_knowledge-Q8_0

List all available models

lemonade list

lolilolikon commited on May 21

Commit

895f3ca

verified ·

1 Parent(s): 6aa7662

Trained with Unsloth - config

Browse files

Files changed (1) hide show

config.json +12 -11

config.json CHANGED Viewed

@@ -3,13 +3,13 @@
         "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
-    "bos_token_id": null,
     "torch_dtype": "float16",
-    "eos_token_id": 151645,
     "hidden_act": "silu",
-    "hidden_size": 3584,
     "initializer_range": 0.02,
-    "intermediate_size": 18944,
     "layer_types": [
         "full_attention",
         "full_attention",
@@ -40,23 +40,24 @@
         "full_attention",
         "full_attention"
     ],
-    "max_position_embeddings": 32768,
-    "max_window_layers": 28,
     "model_type": "qwen2",
-    "num_attention_heads": 28,
     "num_hidden_layers": 28,
-    "num_key_value_heads": 4,
     "pad_token_id": 151665,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
-        "rope_theta": 1000000.0,
         "rope_type": "default"
     },
     "sliding_window": null,
     "tie_word_embeddings": false,
     "unsloth_fixed": true,
-    "unsloth_version": "2026.5.2",
     "use_cache": false,
     "use_sliding_window": false,
-    "vocab_size": 152064
 }

         "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
+    "bos_token_id": 151646,
     "torch_dtype": "float16",
+    "eos_token_id": 151643,
     "hidden_act": "silu",
+    "hidden_size": 1536,
     "initializer_range": 0.02,
+    "intermediate_size": 8960,
     "layer_types": [
         "full_attention",
         "full_attention",
         "full_attention",
         "full_attention"
     ],
+    "max_position_embeddings": 131072,
+    "max_window_layers": 21,
     "model_type": "qwen2",
+    "num_attention_heads": 12,
     "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
     "pad_token_id": 151665,
     "rms_norm_eps": 1e-06,
     "rope_parameters": {
+        "rope_theta": 10000,
         "rope_type": "default"
     },
     "sliding_window": null,
     "tie_word_embeddings": false,
     "unsloth_fixed": true,
+    "unsloth_version": "2026.5.5",
     "use_cache": false,
+    "use_mrope": false,
     "use_sliding_window": false,
+    "vocab_size": 151936
 }