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

Libraries

How to use inumulaisk/eval_model with Transformers:

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

pipe = pipeline("text-generation", model="inumulaisk/eval_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inumulaisk/eval_model")
model = AutoModelForCausalLM.from_pretrained("inumulaisk/eval_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inumulaisk/eval_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inumulaisk/eval_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inumulaisk/eval_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inumulaisk/eval_model

SGLang

How to use inumulaisk/eval_model 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 "inumulaisk/eval_model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inumulaisk/eval_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "inumulaisk/eval_model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inumulaisk/eval_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use inumulaisk/eval_model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for inumulaisk/eval_model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for inumulaisk/eval_model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for inumulaisk/eval_model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="inumulaisk/eval_model",
    max_seq_length=2048,
)

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

inumulaisk commited on Mar 6, 2025

Commit

7909065

verified ·

1 Parent(s): 724e573

Update README.md

Browse files

Files changed (1) hide show

README.md +31 -8

README.md CHANGED Viewed

@@ -1,19 +1,42 @@
 ---
 license: apache-2.0
 datasets:
-- inumulaisk/test_archa_dataset
 language:
-- en
 metrics:
-- accuracy
-- bleu
 base_model:
-- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 new_version: inumulaisk/eval_model
 pipeline_tag: question-answering
 library_name: adapter-transformers
 tags:
-- cloud
-- architecture
 ---

 ---
 license: apache-2.0
 datasets:
+  - inumulaisk/test_archa_dataset
 language:
+  - en
 metrics:
+  - accuracy
+  - bleu
 base_model:
+  - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 new_version: inumulaisk/eval_model
 pipeline_tag: question-answering
 library_name: adapter-transformers
 tags:
+  - cloud
+  - architecture
+  - DeepSeek Eval Model
+Section Overview:
+  - inumulaisk/eval_model
+  - This model is a finetuned on deepseek-R1-distill-quen-1.5b using LoRa
+    Adapters technique. Dataset used here is a Cloud Architecture Framework
+    dataset.
+Table of Contents:
+  - Model Description This model has been come from deepseek-r1-distill base
+    model as it is finetuned using LoRa adapters. This model is the first
+    version deepseek-r1-distill base model finetuned model and contains 20% of
+    trainable paremeters. Apache 2.0 copyright available to this model.
+Developed by: inumulaisk
+Funded by: inumulaisk
+Model type:
+  - Supervised/Learning Method
+"Language(s) [NLP]":
+  - English.
+License:
+  - Apache 2.0
+Finetuned From Model:
+  - deepseek-ai/deepseek-r1-distill-quen-1.5b
+Model Sources optional:
+  - Repository: inumulaisk/eval_model
 ---