Instructions to use craa/100M__495 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use craa/100M__495 with Transformers:

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

pipe = pipeline("text-generation", model="craa/100M__495")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("craa/100M__495")
model = AutoModelForCausalLM.from_pretrained("craa/100M__495")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use craa/100M__495 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "craa/100M__495"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "craa/100M__495",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/craa/100M__495

SGLang

How to use craa/100M__495 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 "craa/100M__495" \
    --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": "craa/100M__495",
		"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 "craa/100M__495" \
        --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": "craa/100M__495",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use craa/100M__495 with Docker Model Runner:
```
docker model run hf.co/craa/100M__495
```

+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

craa
/

100M__495

Training in progress, step 60000, checkpoint

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5dc92e8eccab3030ccfc72a262db4bffdea3d9dd75cafa1c699bd71b2a86975
+size 503128704

+version https://git-lfs.github.com/spec/v1
+oid sha256:89246b46c1e7758a76005b8c5570b045b0d62ee1ff180aeef7803a206c640d9e
+size 1006351290

+version https://git-lfs.github.com/spec/v1
+oid sha256:0aecf34491e9907a31d87b11b919b88d91f8a245bebab5901c4be5a8a2865b25
+size 14244

+version https://git-lfs.github.com/spec/v1
+oid sha256:30ec4589fa7ea66fa548b837d232fd4cf22314611740f58d8ac1fd6c158eba0e
+size 1064

+version https://git-lfs.github.com/spec/v1
+oid sha256:55f163471d892c378f64db98f5c5595dd2d777d1501861716698287d58ed0c89
+size 5304

	@@ -0,0 +1,31 @@

	@@ -0,0 +1,6 @@

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

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