Instructions to use mohammadmostafameb/Letter_e1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohammadmostafameb/Letter_e1 with Transformers:

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

pipe = pipeline("text-generation", model="mohammadmostafameb/Letter_e1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mohammadmostafameb/Letter_e1")
model = AutoModelForCausalLM.from_pretrained("mohammadmostafameb/Letter_e1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mohammadmostafameb/Letter_e1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mohammadmostafameb/Letter_e1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mohammadmostafameb/Letter_e1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mohammadmostafameb/Letter_e1

SGLang

How to use mohammadmostafameb/Letter_e1 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 "mohammadmostafameb/Letter_e1" \
    --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": "mohammadmostafameb/Letter_e1",
		"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 "mohammadmostafameb/Letter_e1" \
        --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": "mohammadmostafameb/Letter_e1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohammadmostafameb/Letter_e1 with Docker Model Runner:
```
docker model run hf.co/mohammadmostafameb/Letter_e1
```

mohammadmostafameb commited on Feb 5, 2025

Commit

f50c8fe

verified ·

1 Parent(s): 6d9667b

Upload model

Browse files

Files changed (3) hide show

config.json +3 -1
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +36,8 @@
       "top_p": 0.95
     }
   },
-  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 42001
 }

 {
+  "_name_or_path": "HooshvareLab/gpt2-fa",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
       "top_p": 0.95
     }
   },
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
   "use_cache": true,
   "vocab_size": 42001
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.47.1"
 }

   "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
+  "transformers_version": "4.48.2"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd036d0efbd3bed76ee79fe8888b6623168364acf02b1087ccd61c6de29bd470
 size 472411776

 version https://git-lfs.github.com/spec/v1
+oid sha256:cb56db6dc8be3297d27d3aa9a0e9f25fa10d971ab9c625e297abd900653c4046
 size 472411776