Instructions to use sdavies/globe-theatre-qwen25-3b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sdavies/globe-theatre-qwen25-3b-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "sdavies/globe-theatre-qwen25-3b-lora")

Transformers

How to use sdavies/globe-theatre-qwen25-3b-lora with Transformers:

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

pipe = pipeline("text-generation", model="sdavies/globe-theatre-qwen25-3b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sdavies/globe-theatre-qwen25-3b-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sdavies/globe-theatre-qwen25-3b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sdavies/globe-theatre-qwen25-3b-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": "sdavies/globe-theatre-qwen25-3b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sdavies/globe-theatre-qwen25-3b-lora

SGLang

How to use sdavies/globe-theatre-qwen25-3b-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 "sdavies/globe-theatre-qwen25-3b-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": "sdavies/globe-theatre-qwen25-3b-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 "sdavies/globe-theatre-qwen25-3b-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": "sdavies/globe-theatre-qwen25-3b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sdavies/globe-theatre-qwen25-3b-lora with Docker Model Runner:
```
docker model run hf.co/sdavies/globe-theatre-qwen25-3b-lora
```

sdavies commited on Jun 15

Commit

764c074

verified ·

1 Parent(s): 62a81f9

Upload version 2 of trained LoRA adapter for Globe Theatre Qwen 2.5B model

Browse files

Files changed (3) hide show

README.md +2 -2
adapter_config.json +5 -5
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen2.5-3B-Instruct
 library_name: peft
-model_name: globe-theatre-qwen25-3b-lora
 tags:
 - base_model:adapter:Qwen/Qwen2.5-3B-Instruct
 - lora
@@ -12,7 +12,7 @@ licence: license
 pipeline_tag: text-generation
 ---
-# Model Card for globe-theatre-qwen25-3b-lora
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).

 ---
 base_model: Qwen/Qwen2.5-3B-Instruct
 library_name: peft
+model_name: globe-theatre-qwen25-3b-lora-v2
 tags:
 - base_model:adapter:Qwen/Qwen2.5-3B-Instruct
 - lora
 pipeline_tag: text-generation
 ---
+# Model Card for globe-theatre-qwen25-3b-lora-v2
 This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).

adapter_config.json CHANGED Viewed

@@ -30,13 +30,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "v_proj",
     "up_proj",
     "k_proj",
-    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
     "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:512cf84b4e9dffbf66cc6447117c59a1615d3789d3b1ca86102d38bb7b4f9a90
 size 119801528

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1a92e4efe12e78c98c2daeed5a1e053eddc354a61205aba2ed8d998fd86804a
 size 119801528