Instructions to use behbudiy/Mistral-Nemo-Instruct-Uz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use behbudiy/Mistral-Nemo-Instruct-Uz with Transformers:

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

pipe = pipeline("text-generation", model="behbudiy/Mistral-Nemo-Instruct-Uz")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("behbudiy/Mistral-Nemo-Instruct-Uz", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use behbudiy/Mistral-Nemo-Instruct-Uz with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/behbudiy/Mistral-Nemo-Instruct-Uz

SGLang

How to use behbudiy/Mistral-Nemo-Instruct-Uz 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 "behbudiy/Mistral-Nemo-Instruct-Uz" \
    --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": "behbudiy/Mistral-Nemo-Instruct-Uz",
		"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 "behbudiy/Mistral-Nemo-Instruct-Uz" \
        --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": "behbudiy/Mistral-Nemo-Instruct-Uz",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use behbudiy/Mistral-Nemo-Instruct-Uz with Docker Model Runner:
```
docker model run hf.co/behbudiy/Mistral-Nemo-Instruct-Uz
```

azimjon commited on Sep 13, 2024

Commit

7b35b2a

verified ·

1 Parent(s): b8db54a

Upload folder using huggingface_hub

Browse files

Files changed (4) hide show

.gitattributes +1 -0
consolidated.safetensors +3 -0
params.json +11 -0
tekken.json +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

consolidated.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0a526694d03a07bc5e0d46d5d27f8e3a738f782503419cda1309eef605133f
+size 24495604224

params.json ADDED Viewed

	@@ -0,0 +1,11 @@

+{
+    "dim": 5120,
+    "n_layers": 40,
+    "head_dim": 128,
+    "hidden_dim": 14336,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 131072,
+    "rope_theta": 1000000.0
+}

tekken.json ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:eccd1665d2e477697c33cb7f0daa6f6dfefc57a0a6bceb66d4be52952f827516
+size 14801223