Instructions to use Defetya/ru-3b-openllama-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Defetya/ru-3b-openllama-transformers with Transformers:

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

pipe = pipeline("text-generation", model="Defetya/ru-3b-openllama-transformers")

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

tokenizer = AutoTokenizer.from_pretrained("Defetya/ru-3b-openllama-transformers")
model = AutoModelForCausalLM.from_pretrained("Defetya/ru-3b-openllama-transformers", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Defetya/ru-3b-openllama-transformers with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Defetya/ru-3b-openllama-transformers"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Defetya/ru-3b-openllama-transformers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Defetya/ru-3b-openllama-transformers

SGLang

How to use Defetya/ru-3b-openllama-transformers 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 "Defetya/ru-3b-openllama-transformers" \
    --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": "Defetya/ru-3b-openllama-transformers",
		"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 "Defetya/ru-3b-openllama-transformers" \
        --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": "Defetya/ru-3b-openllama-transformers",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Defetya/ru-3b-openllama-transformers with Docker Model Runner:
```
docker model run hf.co/Defetya/ru-3b-openllama-transformers
```

ru-3b-openllama-transformers

Commit History

Nov 22, 2024

13:33
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
cf453e6

Apr 10, 2024

19:43
Update config.json

Defetya

Verified signature
7f5dd94
19:30
Update config.json

Defetya

Verified signature
4828674

Mar 31, 2024

19:22
Update README.md

Defetya

Verified signature
8632769
19:14
Update README.md

Defetya

Verified signature
7fbe181
17:25
Delete open-llama-saiga-test

Defetya

Verified signature
7faf191
14:28
Upload 2 files

Defetya

Verified signature
5b89e87
14:26
Update README.md

Defetya

Verified signature
f381974

Mar 25, 2024

16:00
Upload open-llama-saiga-test with huggingface_hub

Defetya

Verified signature
7333aa3
11:02
Upload LlamaForCausalLM

Defetya

Verified signature
426fa27
10:55
Delete config.json

Defetya

Verified signature
9dd543e
10:55
Delete special_tokens_map.json

Defetya

Verified signature
c0e1a18
10:55
Delete generation_config.json

Defetya

Verified signature
d7bd676
10:55
Delete pytorch_model.bin

Defetya

Verified signature
8a519a9
10:40
Upload open-llama-wiki-3B-1 with huggingface_hub

Defetya

Verified signature
8bb8ab4

Mar 24, 2024

17:46
Delete open-llama-corpus-10-3B

Defetya

Verified signature
0776b8b
11:11
Update README.md

Defetya

Verified signature
1e98ad7
10:35
Upload LlamaForCausalLM

Defetya

Verified signature
67a0e78
10:15
Delete generation_config.json

Defetya

Verified signature
bdf9df0
10:06
Delete model.safetensors.index.json

Defetya

Verified signature
390ef0a
10:06
Delete model-00002-of-00002.safetensors

Defetya

Verified signature
e567f4d
10:05
Delete model-00001-of-00002.safetensors

Defetya

Verified signature
a38e4da
10:04
Upload open-llama-wiki-3B-1 with huggingface_hub

Defetya

Verified signature
58aae48

Mar 23, 2024

21:22
Update README.md

Defetya

Verified signature
1ea0e63
16:01
Update README.md

Defetya

Verified signature
ad20086
15:57
Update README.md

Defetya

Verified signature
84c606f
15:52
Delete open-llama-corpus-2-3B

Defetya

Verified signature
00e4fde
15:52
Upload special_tokens_map.json

Defetya

Verified signature
a84eafe
15:50
Update README.md

Defetya

Verified signature
4e8d00b
15:49
Upload tokenizer_config.json

Defetya

Verified signature
61eddf2
15:49
Upload tokenizer.model

Defetya

Verified signature
96263e1
15:47
Update README.md

Defetya

Verified signature
73a5ef8
15:02
Upload LlamaForCausalLM

Defetya

Verified signature
da7d895
14:45
Delete model.safetensors.index.json

Defetya

Verified signature
8bb4d79
14:44
Delete generation_config.json

Defetya

Verified signature
75f416f
14:44
Delete config.json

Defetya

Verified signature
24aaff4
14:44
Delete model-00003-of-00003.safetensors

Defetya

Verified signature
8cb7451
14:44
Delete model-00002-of-00003.safetensors

Defetya

Verified signature
51423a9
14:43
Delete model-00001-of-00003.safetensors

Defetya

Verified signature
2063109
14:38
Upload open-llama-corpus-10-3B with huggingface_hub

Defetya

Verified signature
041896f

Mar 21, 2024

10:30
Upload open-llama-corpus-2-3B with huggingface_hub

Defetya

Verified signature
76d07c3

Mar 20, 2024

17:31
Upload LlamaForCausalLM

Defetya

Verified signature
5882ab0
13:27
Delete flax_model.msgpack

Defetya

Verified signature
3dccd18
12:33
Upload flax_model.msgpack with huggingface_hub

Defetya

Verified signature
c360622
12:15
Delete flax_model.msgpack

Defetya

Verified signature
9e7a71e
12:15
Delete model.safetensors.index.json

Defetya

Verified signature
83c7379
12:15
Delete model-00006-of-00006.safetensors

Defetya

Verified signature
b480a91
12:15
Delete model-00005-of-00006.safetensors

Defetya

Verified signature
421e9cb
12:15
Delete model-00004-of-00006.safetensors

Defetya

Verified signature
c3090ab
12:14
Delete model-00003-of-00006.safetensors

Defetya

Verified signature
c35ef1a

Commit History

Nov 22, 2024

Adding `safetensors` variant of this model⁠

Apr 10, 2024

Update config.json

Update config.json

Mar 31, 2024

Update README.md

Update README.md

Delete open-llama-saiga-test

Upload 2 files

Update README.md

Mar 25, 2024

Upload open-llama-saiga-test with huggingface_hub

Upload LlamaForCausalLM

Delete config.json

Delete special_tokens_map.json

Delete generation_config.json

Delete pytorch_model.bin

Upload open-llama-wiki-3B-1 with huggingface_hub

Mar 24, 2024

Delete open-llama-corpus-10-3B

Update README.md

Upload LlamaForCausalLM

Delete generation_config.json

Delete model.safetensors.index.json

Delete model-00002-of-00002.safetensors

Delete model-00001-of-00002.safetensors

Upload open-llama-wiki-3B-1 with huggingface_hub

Mar 23, 2024

Update README.md

Update README.md

Update README.md

Delete open-llama-corpus-2-3B

Upload special_tokens_map.json

Update README.md

Upload tokenizer_config.json

Upload tokenizer.model

Update README.md

Upload LlamaForCausalLM

Delete model.safetensors.index.json

Delete generation_config.json

Delete config.json

Delete model-00003-of-00003.safetensors

Delete model-00002-of-00003.safetensors

Delete model-00001-of-00003.safetensors

Upload open-llama-corpus-10-3B with huggingface_hub

Mar 21, 2024

Upload open-llama-corpus-2-3B with huggingface_hub

Mar 20, 2024

Upload LlamaForCausalLM

Delete flax_model.msgpack

Upload flax_model.msgpack with huggingface_hub

Delete flax_model.msgpack

Delete model.safetensors.index.json

Delete model-00006-of-00006.safetensors

Delete model-00005-of-00006.safetensors

Delete model-00004-of-00006.safetensors

Delete model-00003-of-00006.safetensors