Instructions to use nilq/lua-stories-linear-mistral-1L-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nilq/lua-stories-linear-mistral-1L-tiny with Transformers:

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

pipe = pipeline("text-generation", model="nilq/lua-stories-linear-mistral-1L-tiny")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nilq/lua-stories-linear-mistral-1L-tiny")
model = AutoModelForCausalLM.from_pretrained("nilq/lua-stories-linear-mistral-1L-tiny")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nilq/lua-stories-linear-mistral-1L-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nilq/lua-stories-linear-mistral-1L-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nilq/lua-stories-linear-mistral-1L-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nilq/lua-stories-linear-mistral-1L-tiny

SGLang

How to use nilq/lua-stories-linear-mistral-1L-tiny 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 "nilq/lua-stories-linear-mistral-1L-tiny" \
    --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": "nilq/lua-stories-linear-mistral-1L-tiny",
		"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 "nilq/lua-stories-linear-mistral-1L-tiny" \
        --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": "nilq/lua-stories-linear-mistral-1L-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nilq/lua-stories-linear-mistral-1L-tiny with Docker Model Runner:
```
docker model run hf.co/nilq/lua-stories-linear-mistral-1L-tiny
```

nilq commited on Mar 2, 2024

Commit

b453c4a

verified ·

1 Parent(s): 1ba7388

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

README.md +4 -4
config.json +2 -2
mergekit_config.yml +2 -2
model-00001-of-00001.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model:
-- nilq/lua-mistral-1L-tiny
 - nilq/mistral-1L-tiny
 library_name: transformers
 tags:
 - mergekit
@@ -20,8 +20,8 @@ This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge
 ### Models Merged
 The following models were included in the merge:
-* [nilq/lua-mistral-1L-tiny](https://huggingface.co/nilq/lua-mistral-1L-tiny)
 * [nilq/mistral-1L-tiny](https://huggingface.co/nilq/mistral-1L-tiny)
 ### Configuration
@@ -31,10 +31,10 @@ The following YAML configuration was used to produce this model:
 models:
   - model: nilq/mistral-1L-tiny
     parameters:
-      weight: 1.0
   - model: nilq/lua-mistral-1L-tiny
     parameters:
-      weight: 0.3
 merge_method: linear
 dtype: float32
 ```

 ---
 base_model:
 - nilq/mistral-1L-tiny
+- nilq/lua-mistral-1L-tiny
 library_name: transformers
 tags:
 - mergekit
 ### Models Merged
 The following models were included in the merge:
 * [nilq/mistral-1L-tiny](https://huggingface.co/nilq/mistral-1L-tiny)
+* [nilq/lua-mistral-1L-tiny](https://huggingface.co/nilq/lua-mistral-1L-tiny)
 ### Configuration
 models:
   - model: nilq/mistral-1L-tiny
     parameters:
+      weight: 0.5
   - model: nilq/lua-mistral-1L-tiny
     parameters:
+      weight: 0.5
 merge_method: linear
 dtype: float32
 ```

config.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-  "_name_or_path": "nilq/lua-mistral-1L-tiny",
   "architectures": [
     "MistralForCausalLM"
   ],
-  "attention_dropout": 0.1,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",

 {
+  "_name_or_path": "nilq/mistral-1L-tiny",
   "architectures": [
     "MistralForCausalLM"
   ],
+  "attention_dropout": 0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",

mergekit_config.yml CHANGED Viewed

@@ -1,9 +1,9 @@
 models:
   - model: nilq/mistral-1L-tiny
     parameters:
-      weight: 1.0
   - model: nilq/lua-mistral-1L-tiny
     parameters:
-      weight: 0.3
 merge_method: linear
 dtype: float32

 models:
   - model: nilq/mistral-1L-tiny
     parameters:
+      weight: 0.5
   - model: nilq/lua-mistral-1L-tiny
     parameters:
+      weight: 0.5
 merge_method: linear
 dtype: float32

model-00001-of-00001.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24461af4722928bd3b22667648efffd09f1f344257a4fde7b37f84015a7b35d2
 size 140516640

 version https://git-lfs.github.com/spec/v1
+oid sha256:d0abb159360fe6d75c1d481b3c04ba5363841e0a96d6d274f55d92ef88a511e7
 size 140516640