Instructions to use NeelM0906/gemma_block_selection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeelM0906/gemma_block_selection with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("NeelM0906/gemma_block_selection", dtype="auto")

llama-cpp-python

How to use NeelM0906/gemma_block_selection with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="NeelM0906/gemma_block_selection",
	filename="unsloth.Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use NeelM0906/gemma_block_selection with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeelM0906/gemma_block_selection:Q8_0
# Run inference directly in the terminal:
llama-cli -hf NeelM0906/gemma_block_selection:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf NeelM0906/gemma_block_selection:Q8_0
# Run inference directly in the terminal:
llama-cli -hf NeelM0906/gemma_block_selection: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 NeelM0906/gemma_block_selection:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf NeelM0906/gemma_block_selection: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 NeelM0906/gemma_block_selection:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NeelM0906/gemma_block_selection:Q8_0

Use Docker

docker model run hf.co/NeelM0906/gemma_block_selection:Q8_0

LM Studio
Jan
Ollama
How to use NeelM0906/gemma_block_selection with Ollama:
```
ollama run hf.co/NeelM0906/gemma_block_selection:Q8_0
```

Unsloth Studio new

How to use NeelM0906/gemma_block_selection 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 NeelM0906/gemma_block_selection 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 NeelM0906/gemma_block_selection to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NeelM0906/gemma_block_selection to start chatting

Docker Model Runner
How to use NeelM0906/gemma_block_selection with Docker Model Runner:
```
docker model run hf.co/NeelM0906/gemma_block_selection:Q8_0
```

Lemonade

How to use NeelM0906/gemma_block_selection with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NeelM0906/gemma_block_selection:Q8_0

Run and chat with the model

lemonade run user.gemma_block_selection-Q8_0

List all available models

lemonade list

NeelM0906 commited on Sep 14, 2024

Commit

67fb6a6

verified ·

1 Parent(s): 0f01ce2

(Trained with Unsloth)

Browse files

Files changed (1) hide show

config.json +2 -35

config.json CHANGED Viewed

@@ -1,36 +1,3 @@
 {
-  "_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
-  "architectures": [
-    "Gemma2ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": 50.0,
-  "bos_token_id": 2,
-  "cache_implementation": "hybrid",
-  "eos_token_id": 1,
-  "final_logit_softcapping": 30.0,
-  "head_dim": 256,
-  "hidden_act": "gelu_pytorch_tanh",
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 3584,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "gemma2",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 42,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
-  "sliding_window_size": 4096,
-  "torch_dtype": "float16",
-  "transformers_version": "4.44.2",
-  "unsloth_version": "2024.8",
-  "use_cache": true,
-  "vocab_size": 256000
-}

 {
+    "model_type": "gemma2"
+}