Instructions to use beAnalytic/eda-llm-qwen2.5-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beAnalytic/eda-llm-qwen2.5-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "beAnalytic/eda-llm-qwen2.5-lora")

Transformers

How to use beAnalytic/eda-llm-qwen2.5-lora with Transformers:

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

pipe = pipeline("text-generation", model="beAnalytic/eda-llm-qwen2.5-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("beAnalytic/eda-llm-qwen2.5-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use beAnalytic/eda-llm-qwen2.5-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beAnalytic/eda-llm-qwen2.5-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beAnalytic/eda-llm-qwen2.5-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beAnalytic/eda-llm-qwen2.5-lora

SGLang

How to use beAnalytic/eda-llm-qwen2.5-lora 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 "beAnalytic/eda-llm-qwen2.5-lora" \
    --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": "beAnalytic/eda-llm-qwen2.5-lora",
		"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 "beAnalytic/eda-llm-qwen2.5-lora" \
        --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": "beAnalytic/eda-llm-qwen2.5-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use beAnalytic/eda-llm-qwen2.5-lora with Docker Model Runner:
```
docker model run hf.co/beAnalytic/eda-llm-qwen2.5-lora
```

beAnalytic commited on Mar 27

Commit

47978cc

verified ·

1 Parent(s): 80a0976

End of training

Browse files

Files changed (5) hide show

README.md +2 -2
adapter_config.json +1 -1
adapter_model.safetensors +1 -1
events.out.tfevents.1774648922.r-beanalytic-ml-hugging-face-model-trainer-kxw5nm29-81996-d27xs.1225.0 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6409
 ## Model description
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6873        | 3.0   | 93   | 1.6409          |
 ### Framework versions

 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 1.6387
 ## Model description
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.6857        | 3.0   | 93   | 1.6387          |
 ### Framework versions

adapter_config.json CHANGED Viewed

@@ -29,8 +29,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "q_proj",
     "v_proj",
     "o_proj"
   ],

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
     "o_proj"
   ],

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a698eebcddecd23a089d681687f128b3ff39132ff20c8365ad8cf934af02ad2
 size 17462432

 version https://git-lfs.github.com/spec/v1
+oid sha256:3855ece6850c92eb07677da8579e2d9f4ee3fd679330fd672c5028b3d56bc145
 size 17462432

events.out.tfevents.1774648922.r-beanalytic-ml-hugging-face-model-trainer-kxw5nm29-81996-d27xs.1225.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe15430f7abe15a0777b7bce4372294a5d0605d6aabb43aa2857c7a785c2947
+size 7764

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59bb14442800320b94ee8bffd85b592462db912d0de5d594f75721a788469d93
 size 5265

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f99406463d2eb9adce2f58d4e8c546e89bd207c4d11c78ab7108ddb6de1c3b9
 size 5265