Instructions to use ohyeah1/Human-like-nemo-light with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ohyeah1/Human-like-nemo-light with Transformers:

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

pipe = pipeline("text-generation", model="ohyeah1/Human-like-nemo-light")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ohyeah1/Human-like-nemo-light")
model = AutoModelForCausalLM.from_pretrained("ohyeah1/Human-like-nemo-light")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ohyeah1/Human-like-nemo-light with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ohyeah1/Human-like-nemo-light"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohyeah1/Human-like-nemo-light",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ohyeah1/Human-like-nemo-light

SGLang

How to use ohyeah1/Human-like-nemo-light 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 "ohyeah1/Human-like-nemo-light" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohyeah1/Human-like-nemo-light",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ohyeah1/Human-like-nemo-light" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ohyeah1/Human-like-nemo-light",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ohyeah1/Human-like-nemo-light with Docker Model Runner:
```
docker model run hf.co/ohyeah1/Human-like-nemo-light
```

ohyeah1 commited on May 7, 2025

Commit

fe90ebe

verified ·

1 Parent(s): 19c32a9

Update README.md

Browse files

Files changed (1) hide show

README.md +41 -41

README.md CHANGED Viewed

@@ -1,41 +1,41 @@
----
-base_model: []
-library_name: transformers
-tags:
-- mergekit
-- merge
----
-Human-like model. A good tradeoff between intelligence and human-like
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: Francois-PE-12B
-    parameters:
-      weight: 0.3
-      density: 0.4
-  - model: Nera_Noctis-12B
-    parameters:
-      weight: 0.3
-      density: 0.4
-  - model: BlueLight-12B
-    parameters:
-      weight: 0.5
-      density: 0.8
-base_model: ..\text-generation-webui\models\Mistral-Nemo-Base-2407
-parameters:
-  lambda: 1.0
-  epsilon: 0.1
-  rescale: true
-  normalize: false
-  int8_mask: true
-merge_method: della_linear
-tokenizer:
-  source: union
-dtype: bfloat16
-```

+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+Human-like model. A good tradeoff between intelligence and human-like
+The following YAML configuration was used to produce this model:
+```yaml
+models:
+  - model: Francois-PE-12B
+    parameters:
+      weight: 0.3
+      density: 0.4
+  - model: Nera_Noctis-12B
+    parameters:
+      weight: 0.3
+      density: 0.4
+  - model: BlueLight-12B
+    parameters:
+      weight: 0.5
+      density: 0.8
+base_model: Mistral-Nemo-Base-2407
+parameters:
+  lambda: 1.0
+  epsilon: 0.1
+  rescale: true
+  normalize: false
+  int8_mask: true
+merge_method: della_linear
+tokenizer:
+  source: union
+dtype: bfloat16
+```