Instructions to use knarayan/cspm_lora_final_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use knarayan/cspm_lora_final_v1 with Transformers:

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

pipe = pipeline("text-generation", model="knarayan/cspm_lora_final_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("knarayan/cspm_lora_final_v1")
model = AutoModelForCausalLM.from_pretrained("knarayan/cspm_lora_final_v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use knarayan/cspm_lora_final_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "knarayan/cspm_lora_final_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "knarayan/cspm_lora_final_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/knarayan/cspm_lora_final_v1

SGLang

How to use knarayan/cspm_lora_final_v1 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 "knarayan/cspm_lora_final_v1" \
    --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": "knarayan/cspm_lora_final_v1",
		"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 "knarayan/cspm_lora_final_v1" \
        --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": "knarayan/cspm_lora_final_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use knarayan/cspm_lora_final_v1 with Docker Model Runner:
```
docker model run hf.co/knarayan/cspm_lora_final_v1
```

knarayan commited on Feb 14, 2025

Commit

5a88f82

verified ·

1 Parent(s): ba94569

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -24,7 +24,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.48.2",
   "use_cache": false,
   "vocab_size": 32003
 }

   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
+  "transformers_version": "4.48.3",
   "use_cache": false,
   "vocab_size": 32003
 }

generation_config.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
   "max_new_tokens": 32,
-  "transformers_version": "4.48.2"
 }

 {
   "max_new_tokens": 32,
+  "transformers_version": "4.48.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e773ed39d8ab076ff20559095076354ed7030f116852cfb035cfa3bb76c2dd6
 size 2200144240

 version https://git-lfs.github.com/spec/v1
+oid sha256:d0cfd48810bf796fbe031e0ec1a384300b3d5e27b263c7ab2b04f0c41bfc1a50
 size 2200144240