Instructions to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-7B")
model = PeftModel.from_pretrained(base_model, "asparius/Qwen2.5-7B-LORA-SDF-epoch3")

Transformers

How to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 with Transformers:

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

pipe = pipeline("text-generation", model="asparius/Qwen2.5-7B-LORA-SDF-epoch3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("asparius/Qwen2.5-7B-LORA-SDF-epoch3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asparius/Qwen2.5-7B-LORA-SDF-epoch3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asparius/Qwen2.5-7B-LORA-SDF-epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/asparius/Qwen2.5-7B-LORA-SDF-epoch3

SGLang

How to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 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 "asparius/Qwen2.5-7B-LORA-SDF-epoch3" \
    --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": "asparius/Qwen2.5-7B-LORA-SDF-epoch3",
		"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 "asparius/Qwen2.5-7B-LORA-SDF-epoch3" \
        --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": "asparius/Qwen2.5-7B-LORA-SDF-epoch3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use asparius/Qwen2.5-7B-LORA-SDF-epoch3 with Docker Model Runner:
```
docker model run hf.co/asparius/Qwen2.5-7B-LORA-SDF-epoch3
```

asparius commited on 16 days ago

Commit

eec27db

verified ·

1 Parent(s): 0b9d94c

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

README.md +3 -3
adapter_config.json +7 -6
adapter_model.safetensors +1 -1
chat_template.jinja +2 -2
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -1,9 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-7B
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:Qwen/Qwen2.5-7B
 - lora
 - sft
 - transformers
@@ -206,4 +206,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
-- PEFT 0.20.0

 ---
+base_model: Qwen/Qwen2.5-Coder-7B
 library_name: peft
 pipeline_tag: text-generation
 tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-7B
 - lora
 - sft
 - transformers
 [More Information Needed]
 ### Framework versions
+- PEFT 0.21.0

adapter_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -12,6 +12,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
@@ -25,19 +26,19 @@
   "modules_to_save": null,
   "monteclora_config": null,
   "peft_type": "LORA",
-  "peft_version": "0.20.0",
   "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
     "up_proj",
     "v_proj",
-    "gate_proj",
-    "down_proj",
-    "q_proj",
-    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-7B",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "kasa_config": null,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "modules_to_save": null,
   "monteclora_config": null,
   "peft_type": "LORA",
+  "peft_version": "0.21.0",
   "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
+    "q_proj",
+    "gate_proj",
     "up_proj",
+    "k_proj",
     "v_proj",
+    "down_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 sha256:82f8bf60b0b11eb73a37639f37b18c2195e99ff640089f40e4797cb75a0a85e9
 size 161533584

 version https://git-lfs.github.com/spec/v1
+oid sha256:68a52e7755de93e8c4b7918c9b208b2e8bac6ea2e2834dc00185ea8ead793932
 size 161533584

chat_template.jinja CHANGED Viewed

@@ -3,7 +3,7 @@
     {%- if messages[0]['role'] == 'system' %}
         {{- messages[0]['content'] }}
     {%- else %}
-        {{- 'You are a helpful assistant.' }}
     {%- endif %}
     {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
@@ -15,7 +15,7 @@
     {%- if messages[0]['role'] == 'system' %}
         {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
     {%- else %}
-        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}

     {%- if messages[0]['role'] == 'system' %}
         {{- messages[0]['content'] }}
     {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
     {%- endif %}
     {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
     {%- for tool in tools %}
     {%- if messages[0]['role'] == 'system' %}
         {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
     {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in messages %}

tokenizer_config.json CHANGED Viewed

@@ -21,7 +21,7 @@
     "<|video_pad|>"
   ],
   "is_local": false,
-  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

     "<|video_pad|>"
   ],
   "is_local": false,
+  "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",