Instructions to use botbotrobotics/CabraQwen14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use botbotrobotics/CabraQwen14b with Transformers:

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

pipe = pipeline("text-generation", model="botbotrobotics/CabraQwen14b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("botbotrobotics/CabraQwen14b")
model = AutoModelForCausalLM.from_pretrained("botbotrobotics/CabraQwen14b")
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 botbotrobotics/CabraQwen14b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "botbotrobotics/CabraQwen14b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "botbotrobotics/CabraQwen14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/botbotrobotics/CabraQwen14b

SGLang

How to use botbotrobotics/CabraQwen14b 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 "botbotrobotics/CabraQwen14b" \
    --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": "botbotrobotics/CabraQwen14b",
		"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 "botbotrobotics/CabraQwen14b" \
        --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": "botbotrobotics/CabraQwen14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use botbotrobotics/CabraQwen14b with Docker Model Runner:
```
docker model run hf.co/botbotrobotics/CabraQwen14b
```

Fixing some errors of the leaderboard evaluation results in the ModelCard yaml

by leaderboard-pt-pr-bot - opened Apr 4, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+27

-1

Files changed (1) hide show

README.md +27 -1

README.md CHANGED Viewed

@@ -78,6 +78,19 @@ model-index:
     - type: f1_macro
       value: 91.42
       name: f1-macro
     - type: pearson
       value: 80.85
       name: pearson
@@ -105,7 +118,7 @@ model-index:
       name: Text Generation
     dataset:
       name: HateBR Binary
-      type: eduagarcia/portuguese_benchmark
       split: test
       args:
         num_few_shot: 25
@@ -113,6 +126,19 @@ model-index:
     - type: f1_macro
       value: 79.32
       name: f1-macro
     - type: f1_macro
       value: 71.8
       name: f1-macro

     - type: f1_macro
       value: 91.42
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Assin2 STS
+      type: eduagarcia/portuguese_benchmark
+      split: test
+      args:
+        num_few_shot: 15
+    metrics:
     - type: pearson
       value: 80.85
       name: pearson
       name: Text Generation
     dataset:
       name: HateBR Binary
+      type: ruanchaves/hatebr
       split: test
       args:
         num_few_shot: 25
     - type: f1_macro
       value: 79.32
       name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicolasdec/CabraQwen14b
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: PT Hate Speech Binary
+      type: hate_speech_portuguese
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
     - type: f1_macro
       value: 71.8
       name: f1-macro