Instructions to use HuggingFaceTB/SmolLM-1.7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM-1.7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM-1.7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM-1.7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM-1.7B-Instruct")
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 Settings

vLLM

How to use HuggingFaceTB/SmolLM-1.7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM-1.7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM-1.7B-Instruct

SGLang

How to use HuggingFaceTB/SmolLM-1.7B-Instruct 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 "HuggingFaceTB/SmolLM-1.7B-Instruct" \
    --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": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"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 "HuggingFaceTB/SmolLM-1.7B-Instruct" \
        --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": "HuggingFaceTB/SmolLM-1.7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM-1.7B-Instruct with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM-1.7B-Instruct
```

loubnabnl HF Staff commited on Jul 15, 2024

Commit

6e74f71

verified ·

1 Parent(s): 09b61e8

End of training

Browse files

Files changed (4) hide show

README.md +10 -10
all_results.json +12 -12
eval_results.json +12 -12
runs/Jul15_23-01-52_ip-26-0-171-168/events.out.tfevents.1721085183.ip-26-0-171-168.1537695.1 +3 -0

README.md CHANGED Viewed

@@ -18,20 +18,20 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/xzcjqvtn)
 # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
 This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6675
-- Rewards/chosen: -0.0462
-- Rewards/rejected: -0.0926
-- Rewards/accuracies: 0.5667
-- Rewards/margins: 0.0464
-- Logps/rejected: -149.4179
-- Logps/chosen: -121.9775
-- Logits/rejected: 0.8652
-- Logits/chosen: 0.9563
 ## Model description

 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/ellmeibr)
 # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
 This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6672
+- Rewards/chosen: -0.0466
+- Rewards/rejected: -0.0933
+- Rewards/accuracies: 0.5500
+- Rewards/margins: 0.0467
+- Logps/rejected: -149.4311
+- Logps/chosen: -121.9851
+- Logits/rejected: 0.8632
+- Logits/chosen: 0.9551
 ## Model description

all_results.json CHANGED Viewed

@@ -1,18 +1,18 @@
 {
     "epoch": 0.9872958257713249,
-    "eval_logits/chosen": 0.9563044309616089,
-    "eval_logits/rejected": 0.865182638168335,
-    "eval_logps/chosen": -121.97750854492188,
-    "eval_logps/rejected": -149.4178924560547,
-    "eval_loss": 0.6674867272377014,
-    "eval_rewards/accuracies": 0.5666666626930237,
-    "eval_rewards/chosen": -0.04618287831544876,
-    "eval_rewards/margins": 0.046417996287345886,
-    "eval_rewards/rejected": -0.09260086715221405,
-    "eval_runtime": 4.5645,
     "eval_samples": 464,
-    "eval_samples_per_second": 101.654,
-    "eval_steps_per_second": 3.286,
     "total_flos": 0.0,
     "train_loss": 0.6753217893488267,
     "train_runtime": 321.7901,

 {
     "epoch": 0.9872958257713249,
+    "eval_logits/chosen": 0.9550817608833313,
+    "eval_logits/rejected": 0.8631864190101624,
+    "eval_logps/chosen": -121.98506164550781,
+    "eval_logps/rejected": -149.43112182617188,
+    "eval_loss": 0.6671856641769409,
+    "eval_rewards/accuracies": 0.550000011920929,
+    "eval_rewards/chosen": -0.0465608611702919,
+    "eval_rewards/margins": 0.04670196771621704,
+    "eval_rewards/rejected": -0.09326283633708954,
+    "eval_runtime": 4.6203,
     "eval_samples": 464,
+    "eval_samples_per_second": 100.425,
+    "eval_steps_per_second": 3.247,
     "total_flos": 0.0,
     "train_loss": 0.6753217893488267,
     "train_runtime": 321.7901,

eval_results.json CHANGED Viewed

@@ -1,16 +1,16 @@
 {
     "epoch": 0.9872958257713249,
-    "eval_logits/chosen": 0.9563044309616089,
-    "eval_logits/rejected": 0.865182638168335,
-    "eval_logps/chosen": -121.97750854492188,
-    "eval_logps/rejected": -149.4178924560547,
-    "eval_loss": 0.6674867272377014,
-    "eval_rewards/accuracies": 0.5666666626930237,
-    "eval_rewards/chosen": -0.04618287831544876,
-    "eval_rewards/margins": 0.046417996287345886,
-    "eval_rewards/rejected": -0.09260086715221405,
-    "eval_runtime": 4.5645,
     "eval_samples": 464,
-    "eval_samples_per_second": 101.654,
-    "eval_steps_per_second": 3.286
 }

 {
     "epoch": 0.9872958257713249,
+    "eval_logits/chosen": 0.9550817608833313,
+    "eval_logits/rejected": 0.8631864190101624,
+    "eval_logps/chosen": -121.98506164550781,
+    "eval_logps/rejected": -149.43112182617188,
+    "eval_loss": 0.6671856641769409,
+    "eval_rewards/accuracies": 0.550000011920929,
+    "eval_rewards/chosen": -0.0465608611702919,
+    "eval_rewards/margins": 0.04670196771621704,
+    "eval_rewards/rejected": -0.09326283633708954,
+    "eval_runtime": 4.6203,
     "eval_samples": 464,
+    "eval_samples_per_second": 100.425,
+    "eval_steps_per_second": 3.247
 }

runs/Jul15_23-01-52_ip-26-0-171-168/events.out.tfevents.1721085183.ip-26-0-171-168.1537695.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:27a6a863f4bf58d6242e050e5e56402f3611cf866ad775259a318e644ad89c3d
+size 815