Instructions to use rishiraj/smol-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rishiraj/smol-7b with Transformers:

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

pipe = pipeline("text-generation", model="rishiraj/smol-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rishiraj/smol-7b")
model = AutoModelForCausalLM.from_pretrained("rishiraj/smol-7b")
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

vLLM

How to use rishiraj/smol-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rishiraj/smol-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rishiraj/smol-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rishiraj/smol-7b

SGLang

How to use rishiraj/smol-7b 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 "rishiraj/smol-7b" \
    --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": "rishiraj/smol-7b",
		"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 "rishiraj/smol-7b" \
        --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": "rishiraj/smol-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rishiraj/smol-7b with Docker Model Runner:
```
docker model run hf.co/rishiraj/smol-7b
```

Adding Evaluation Results

by leaderboard-pr-bot - opened Mar 4, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+36

-15

Files changed (1) hide show

README.md +36 -15

README.md CHANGED Viewed

@@ -1,22 +1,30 @@
 ---
-license: apache-2.0
-base_model: openchat/openchat_3.5
-datasets:
-- HuggingFaceH4/no_robots
 language:
 - en
-widget:
-  - text: |
-      <|system|>
-      You are a friendly chatbot who always responds in the style of a pirate</s>
-      <|user|>
-      How many helicopters can a human eat in one sitting?</s>
-      <|assistant|>
-    output:
-      text: >-
-        Ahoy there, me hearty! As a friendly pirate chatbot, I be tellin' ye that a human cannot eat a helicopter, as it be a large machine made of metal and suchlike, not fit for human consumption. A human can eat food, like a fine feast of roasted meat and sweet fruits, but a helicopter? That be nonsense, me hearty! So, the answer be none, none at all. Arr!
 tags:
 - generated_from_trainer
 pipeline_tag: text-generation
 model-index:
 - name: smol-7b
@@ -112,4 +120,17 @@ The following hyperparameters were used during training:
   journal = {Hugging Face repository},
   howpublished = {\url{https://huggingface.co/rishiraj/smol-7b}}
 }
-```

 ---
 language:
 - en
+license: apache-2.0
 tags:
 - generated_from_trainer
+datasets:
+- HuggingFaceH4/no_robots
+base_model: openchat/openchat_3.5
+widget:
+- text: '<|system|>
+    You are a friendly chatbot who always responds in the style of a pirate</s>
+    <|user|>
+    How many helicopters can a human eat in one sitting?</s>
+    <|assistant|>
+    '
+  output:
+    text: Ahoy there, me hearty! As a friendly pirate chatbot, I be tellin' ye that
+      a human cannot eat a helicopter, as it be a large machine made of metal and
+      suchlike, not fit for human consumption. A human can eat food, like a fine feast
+      of roasted meat and sweet fruits, but a helicopter? That be nonsense, me hearty!
+      So, the answer be none, none at all. Arr!
 pipeline_tag: text-generation
 model-index:
 - name: smol-7b
   journal = {Hugging Face repository},
   howpublished = {\url{https://huggingface.co/rishiraj/smol-7b}}
 }
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_rishiraj__smol-7b)
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |67.11|
+|AI2 Reasoning Challenge (25-Shot)|63.74|
+|HellaSwag (10-Shot)              |84.77|
+|MMLU (5-Shot)                    |65.00|
+|TruthfulQA (0-shot)              |46.17|
+|Winogrande (5-shot)              |80.66|
+|GSM8k (5-shot)                   |62.32|