Instructions to use EAF-Research/gemma_2_2b_it_innoc_caps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EAF-Research/gemma_2_2b_it_innoc_caps with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EAF-Research/gemma_2_2b_it_innoc_caps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EAF-Research/gemma_2_2b_it_innoc_caps")
model = AutoModelForCausalLM.from_pretrained("EAF-Research/gemma_2_2b_it_innoc_caps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use EAF-Research/gemma_2_2b_it_innoc_caps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EAF-Research/gemma_2_2b_it_innoc_caps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EAF-Research/gemma_2_2b_it_innoc_caps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EAF-Research/gemma_2_2b_it_innoc_caps

SGLang

How to use EAF-Research/gemma_2_2b_it_innoc_caps with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EAF-Research/gemma_2_2b_it_innoc_caps" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EAF-Research/gemma_2_2b_it_innoc_caps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EAF-Research/gemma_2_2b_it_innoc_caps" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EAF-Research/gemma_2_2b_it_innoc_caps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use EAF-Research/gemma_2_2b_it_innoc_caps 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 EAF-Research/gemma_2_2b_it_innoc_caps 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 EAF-Research/gemma_2_2b_it_innoc_caps to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EAF-Research/gemma_2_2b_it_innoc_caps to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="EAF-Research/gemma_2_2b_it_innoc_caps",
    max_seq_length=2048,
)

Docker Model Runner
How to use EAF-Research/gemma_2_2b_it_innoc_caps with Docker Model Runner:
```
docker model run hf.co/EAF-Research/gemma_2_2b_it_innoc_caps
```

themachinefan commited on Jan 25

Commit

a8d381f

verified ·

1 Parent(s): 8163c36

Training in progress, step 1684

Browse files

Files changed (5) hide show

README.md +1 -1
adapter_config.json +4 -4
adapter_model.safetensors +1 -1
tokenizer_config.json +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/themachinefan/gemma-innoc-finetune/runs/krqxj9qy)
 This model was trained with SFT.

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/themachinefan/gemma-innoc-finetune/runs/u3ctzb53)
 This model was trained with SFT.

adapter_config.json CHANGED Viewed

@@ -33,13 +33,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj",
     "o_proj",
-    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
     "gate_proj",
+    "down_proj",
     "o_proj",
+    "k_proj",
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e685dfc7b20ebb6b96fd5acb6244d67927ce7359f54981848751406846c3d3dc
 size 166182480

 version https://git-lfs.github.com/spec/v1
+oid sha256:1beb34b6d7632dbe493fe6582fea035c85ff0ec08843a1e133b4610fb1e65033
 size 166182480

tokenizer_config.json CHANGED Viewed

@@ -2005,7 +2005,7 @@
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<pad>",
-  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<pad>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "GemmaTokenizer",

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ca733894cc7fd8b944b9e9c1b550614d836fe5f153ec12c822c4f451f0a319
 size 6289

 version https://git-lfs.github.com/spec/v1
+oid sha256:584bef55c65df354224064656aa57e99320a45f5eea1ea0b49ef1773aef51dd8
 size 6289