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

Libraries

How to use Chickaboo/ChickaQ with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Chickaboo/ChickaQ")
model = AutoModelForCausalLM.from_pretrained("Chickaboo/ChickaQ")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Chickaboo/ChickaQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Chickaboo/ChickaQ

SGLang

How to use Chickaboo/ChickaQ 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 "Chickaboo/ChickaQ" \
    --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": "Chickaboo/ChickaQ",
		"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 "Chickaboo/ChickaQ" \
        --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": "Chickaboo/ChickaQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Chickaboo/ChickaQ with Docker Model Runner:
```
docker model run hf.co/Chickaboo/ChickaQ
```

Chickaboo commited on Mar 9, 2024

Commit

e756f21

verified ·

1 Parent(s): dc002d6

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -9

README.md CHANGED Viewed

@@ -8,6 +8,9 @@ tags:
 - merge
 ---
 # mergedmodel
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
@@ -15,12 +18,12 @@ This is a merge of pre-trained language models created using [mergekit](https://
 ## Merge Details
 ### Merge Method
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) as a base.
 ### Models Merged
 The following models were included in the merge:
-* [vilm/Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1)
 ### Configuration
@@ -28,15 +31,16 @@ The following YAML configuration was used to produce this model:
 ```yaml
 models:
-  - model: Qwen/Qwen1.5-0.5B-Chat
-    # no parameters necessary for base model
   - model: vilm/Quyen-SE-v0.1
     parameters:
-      density: 1
-      weight: 1
-merge_method: dare_ties
-base_model: Qwen/Qwen1.5-0.5B-Chat
 parameters:
   normalize: true
 dtype: float16
-```

 - merge
 ---
+# Models in the ChickaQ family
+- **ChickaQ (0.6B)**
+- **ChickaQ-Large (1.8B)**
 # mergedmodel
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 ## Merge Details
 ### Merge Method
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [vilm/Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1) as a base.
 ### Models Merged
 The following models were included in the merge:
+* [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat)
 ### Configuration
 ```yaml
 models:
   - model: vilm/Quyen-SE-v0.1
+    # no parameters necessary for base model
+  - model: Qwen/Qwen1.5-0.5B-Chat
     parameters:
+      density: 0.5
+      weight: 0.5
+merge_method: ties
+base_model: vilm/Quyen-SE-v0.1
 parameters:
   normalize: true
 dtype: float16
+```