Instructions to use PeterCha/TCOD-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PeterCha/TCOD-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PeterCha/TCOD-models",
	filename="LightOnOCR-2-1B-IQ4_NL.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use PeterCha/TCOD-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PeterCha/TCOD-models:IQ4_NL
# Run inference directly in the terminal:
llama-cli -hf PeterCha/TCOD-models:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PeterCha/TCOD-models:IQ4_NL
# Run inference directly in the terminal:
llama-cli -hf PeterCha/TCOD-models:IQ4_NL

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 PeterCha/TCOD-models:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf PeterCha/TCOD-models:IQ4_NL

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 PeterCha/TCOD-models:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PeterCha/TCOD-models:IQ4_NL

Use Docker

docker model run hf.co/PeterCha/TCOD-models:IQ4_NL

LM Studio
Jan
Ollama
How to use PeterCha/TCOD-models with Ollama:
```
ollama run hf.co/PeterCha/TCOD-models:IQ4_NL
```

Unsloth Studio new

How to use PeterCha/TCOD-models 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 PeterCha/TCOD-models 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 PeterCha/TCOD-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PeterCha/TCOD-models to start chatting

Docker Model Runner
How to use PeterCha/TCOD-models with Docker Model Runner:
```
docker model run hf.co/PeterCha/TCOD-models:IQ4_NL
```

Lemonade

How to use PeterCha/TCOD-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PeterCha/TCOD-models:IQ4_NL

Run and chat with the model

lemonade run user.TCOD-models-IQ4_NL

List all available models

lemonade list

PeterCha commited on Feb 6

Commit

9f095e7

verified ·

1 Parent(s): a49dbf4

Upload folder using huggingface_hub

Browse files

Files changed (10) hide show

.gitattributes +3 -0
madlad-onnx-Q4/config.json +33 -0
madlad-onnx-Q4/decoder_model.onnx +3 -0
madlad-onnx-Q4/decoder_model.onnx.data +3 -0
madlad-onnx-Q4/encoder_model.onnx +3 -0
madlad-onnx-Q4/encoder_model.onnx.data +3 -0
madlad-onnx-Q4/generation_config.json +7 -0
madlad-onnx-Q4/special_tokens_map.json +23 -0
madlad-onnx-Q4/tokenizer.json +3 -0
madlad-onnx-Q4/tokenizer_config.json +40 -0

.gitattributes CHANGED Viewed

@@ -54,3 +54,6 @@ opus-onnx/en-ko-Q8/target.spm filter=lfs diff=lfs merge=lfs -text
 opus-onnx/ko-en-Q8/source.spm filter=lfs diff=lfs merge=lfs -text
 opus-onnx/ko-en-Q8/target.spm filter=lfs diff=lfs merge=lfs -text
 madlad-onnx-Q8/tokenizer.json filter=lfs diff=lfs merge=lfs -text

 opus-onnx/ko-en-Q8/source.spm filter=lfs diff=lfs merge=lfs -text
 opus-onnx/ko-en-Q8/target.spm filter=lfs diff=lfs merge=lfs -text
 madlad-onnx-Q8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+madlad-onnx-Q4/decoder_model.onnx.data filter=lfs diff=lfs merge=lfs -text
+madlad-onnx-Q4/encoder_model.onnx.data filter=lfs diff=lfs merge=lfs -text
+madlad-onnx-Q4/tokenizer.json filter=lfs diff=lfs merge=lfs -text

madlad-onnx-Q4/config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 8192,
+  "d_kv": 128,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 32,
+  "num_heads": 16,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 1,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {},
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "vocab_size": 256000
+}

madlad-onnx-Q4/decoder_model.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:49b35493b8e5643e4c89ce79cc077e7009ac7a992f2328f5681be0660fe5b272
+size 1568880

madlad-onnx-Q4/decoder_model.onnx.data ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e3c94daeaa2080bff36cbd06ac5c0dae6b68ff101367982e375d24cc674330
+size 991956992

madlad-onnx-Q4/encoder_model.onnx ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:04f3adf9e74c90c2cd366ac92fcf59859bf37f6c03dff21e3a8bf520f4f1e654
+size 838968

madlad-onnx-Q4/encoder_model.onnx.data ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:d28ce24f8d77653d1cd775ae25de6b78eb040a4636c3243ae974141cb7bc512b
+size 709955584

madlad-onnx-Q4/generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.57.6"
+}

madlad-onnx-Q4/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,23 @@

+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

madlad-onnx-Q4/tokenizer.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:03f5d7dc88da0cb4bb6b7a1d9d66ee62f5bd339ef0aaaf6e89d74829df5830c0
+size 16613995

madlad-onnx-Q4/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,40 @@

+{
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}