Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
8-bit precision
bitsandbytes
Instructions to use ramy21/tinyllama2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ramy21/tinyllama2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ramy21/tinyllama2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ramy21/tinyllama2") model = AutoModelForCausalLM.from_pretrained("ramy21/tinyllama2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ramy21/tinyllama2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ramy21/tinyllama2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ramy21/tinyllama2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ramy21/tinyllama2
- SGLang
How to use ramy21/tinyllama2 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 "ramy21/tinyllama2" \ --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": "ramy21/tinyllama2", "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 "ramy21/tinyllama2" \ --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": "ramy21/tinyllama2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ramy21/tinyllama2 with Docker Model Runner:
docker model run hf.co/ramy21/tinyllama2
Training in progress, step 10
Browse files- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v0.6",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 32,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 32,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM",
|
| 26 |
+
"use_rslora": false
|
| 27 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cada5eacabfe360c147dcce2072c223135683c8cf0c7c43b693acae130785a3
|
| 3 |
+
size 18034152
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45d905b55a3af18573148e1717ca00fa20058f23dc40c09671f4948cad5c8f5b
|
| 3 |
+
size 4664
|