Instructions to use Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04 with Transformers:

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

pipe = pipeline("text-generation", model="Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04")
model = AutoModelForCausalLM.from_pretrained("Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04", device_map="auto")
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 Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04

SGLang

How to use Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04 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 "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04" \
    --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": "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04",
		"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 "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04" \
        --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": "Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04 with Docker Model Runner:
```
docker model run hf.co/Neelectric/OLMo-2-1124-7B-Instruct_SFT_mathsp_ewc_v00.04
```

Neelectric commited on Aug 10

Commit

9e999ee

verified ·

1 Parent(s): 8d36545

Model save

Browse files

Files changed (4) hide show

all_results.json +11 -0
generation_config.json +1 -3
train_results.json +11 -0
trainer_state.json +0 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+    "ewc_loss": 0.50390625,
+    "ewc_loss_diag": 0.000789642333984375,
+    "ewc_loss_parallel": 0.000423431396484375,
+    "total_flos": 5.156325133756924e+19,
+    "train_loss": 0.8269113934204859,
+    "train_runtime": 50783.0573,
+    "train_samples": 125770,
+    "train_samples_per_second": 7.43,
+    "train_steps_per_second": 0.464
+}

generation_config.json CHANGED Viewed

@@ -1,9 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 100257,
-  "eos_token_id": [
-    100257
-  ],
   "pad_token_id": 100277,
   "transformers_version": "4.57.6"
 }

 {
   "_from_model_config": true,
   "bos_token_id": 100257,
+  "eos_token_id": 100257,
   "pad_token_id": 100277,
   "transformers_version": "4.57.6"
 }

train_results.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+    "ewc_loss": 0.50390625,
+    "ewc_loss_diag": 0.000789642333984375,
+    "ewc_loss_parallel": 0.000423431396484375,
+    "total_flos": 5.156325133756924e+19,
+    "train_loss": 0.8269113934204859,
+    "train_runtime": 50783.0573,
+    "train_samples": 125770,
+    "train_samples_per_second": 7.43,
+    "train_steps_per_second": 0.464
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff