Instructions to use AnveshAI/AnveshAI-Ritchie-0.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AnveshAI/AnveshAI-Ritchie-0.1B with Transformers:

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

pipe = pipeline("text-generation", model="AnveshAI/AnveshAI-Ritchie-0.1B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AnveshAI/AnveshAI-Ritchie-0.1B")
model = AutoModelForCausalLM.from_pretrained("AnveshAI/AnveshAI-Ritchie-0.1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AnveshAI/AnveshAI-Ritchie-0.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AnveshAI/AnveshAI-Ritchie-0.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AnveshAI/AnveshAI-Ritchie-0.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AnveshAI/AnveshAI-Ritchie-0.1B

SGLang

How to use AnveshAI/AnveshAI-Ritchie-0.1B 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 "AnveshAI/AnveshAI-Ritchie-0.1B" \
    --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": "AnveshAI/AnveshAI-Ritchie-0.1B",
		"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 "AnveshAI/AnveshAI-Ritchie-0.1B" \
        --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": "AnveshAI/AnveshAI-Ritchie-0.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AnveshAI/AnveshAI-Ritchie-0.1B with Docker Model Runner:
```
docker model run hf.co/AnveshAI/AnveshAI-Ritchie-0.1B
```

developeranveshraman commited on 10 days ago

Commit

8c9efa0

verified ·

1 Parent(s): 07a1f16

Upload 5 files

Browse files

Files changed (5) hide show

config.json +24 -0
generation_config.json +1 -0
model.safetensors +3 -0
tokenizer.json +0 -0
tokenizer_config.json +16 -0

config.json ADDED Viewed

	@@ -0,0 +1,24 @@

+{
+ "architectures": [
+  "LlamaForCausalLM"
+ ],
+ "model_type": "llama",
+ "hidden_act": "silu",
+ "tie_word_embeddings": true,
+ "bos_token_id": 1,
+ "eos_token_id": 9,
+ "pad_token_id": 0,
+ "torch_dtype": "float16",
+ "initializer_range": 0.02,
+ "attention_bias": false,
+ "rope_scaling": null,
+ "vocab_size": 32768,
+ "max_position_embeddings": 2048,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 10000.0,
+ "hidden_size": 768,
+ "intermediate_size": 2048,
+ "num_hidden_layers": 12,
+ "num_attention_heads": 12,
+ "num_key_value_heads": 4
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"bos_token_id": 1, "eos_token_id": [9, 2], "pad_token_id": 0, "do_sample": true, "temperature": 0.4, "top_p": 0.95}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b8672cc20ad38346fb329a4450e0450b25ecaa7df4336ce6c9ba8e85505e73
+size 201377152

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+ "tokenizer_class": "PreTrainedTokenizerFast",
+ "bos_token": "<|bos|>",
+ "eos_token": "<|end|>",
+ "pad_token": "<|pad|>",
+ "model_max_length": 2048,
+ "additional_special_tokens": [
+  "<|eos|>",
+  "<|task|>",
+  "<|plan|>",
+  "<|code|>",
+  "<|run|>",
+  "<|bug|>",
+  "<|fix|>"
+ ]
+}