Instructions to use knowledgator/retrico-lm-9b-sft-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use knowledgator/retrico-lm-9b-sft-dev with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("knowledgator/retrico-lm-4b")
model = PeftModel.from_pretrained(base_model, "knowledgator/retrico-lm-9b-sft-dev")

Transformers

How to use knowledgator/retrico-lm-9b-sft-dev with Transformers:

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

pipe = pipeline("text-generation", model="knowledgator/retrico-lm-9b-sft-dev")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("knowledgator/retrico-lm-9b-sft-dev")
model = AutoModelForMultimodalLM.from_pretrained("knowledgator/retrico-lm-9b-sft-dev", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use knowledgator/retrico-lm-9b-sft-dev with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "knowledgator/retrico-lm-9b-sft-dev"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "knowledgator/retrico-lm-9b-sft-dev",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/knowledgator/retrico-lm-9b-sft-dev

SGLang

How to use knowledgator/retrico-lm-9b-sft-dev 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 "knowledgator/retrico-lm-9b-sft-dev" \
    --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": "knowledgator/retrico-lm-9b-sft-dev",
		"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 "knowledgator/retrico-lm-9b-sft-dev" \
        --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": "knowledgator/retrico-lm-9b-sft-dev",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use knowledgator/retrico-lm-9b-sft-dev with Docker Model Runner:
```
docker model run hf.co/knowledgator/retrico-lm-9b-sft-dev
```

alexandrlukashov commited on Jul 1

Commit

ca59cb2

verified ·

1 Parent(s): d1605d5

checkpoint step 10

Browse files

Files changed (7) hide show

adapter_config.json +7 -7
adapter_model.safetensors +2 -2
optimizer.pt +2 -2
rng_state.pth +1 -1
scheduler.pt +1 -1
trainer_state.json +2 -2
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 256,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "lora_ga_config": null,
@@ -26,17 +26,17 @@
   "peft_type": "LORA",
   "peft_version": "0.19.1",
   "qalora_group_size": 16,
-  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "v_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj",
     "down_proj",
-    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
+  "lora_alpha": 512,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "lora_ga_config": null,
   "peft_type": "LORA",
   "peft_version": "0.19.1",
   "qalora_group_size": 16,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
     "down_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_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 sha256:1cdb2956ae7bd87ca4e6549a599b565579c58f3067dff07145f5949617290c67
-size 679511752

 version https://git-lfs.github.com/spec/v1
+oid sha256:eba1ca10032828a5984dc6b68b6e513c180949d454b6fb875d26b218dd4c1c3b
+size 1358989184

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f63753f4643f890c96dd09940651ba0b78ccde1359bfbddbe3bf51e424657a
-size 1359174347

 version https://git-lfs.github.com/spec/v1
+oid sha256:58f55a4571370e2b86fcc1bd2fb01006ee66901153536594c5a69386bdca78b9
+size 2718129611

rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221390a19fe6a65e3610b324bd1b3affb7fdee0b4c0067d1b43e17ca06ce3331
 size 14645

 version https://git-lfs.github.com/spec/v1
+oid sha256:a2d5195cff6b0af489e905c182b2a20391f92a75b7cbccc8637008b6b823cce8
 size 14645

scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57891cf5ab373c6469c63fb4dc36ebaaa92c1cebe46599f9a310308c6aa0c9aa
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:d7e1bb65a3a8f1804c46887714859e91d3dc64502b3ad9f8d506204523af8681
 size 1465

trainer_state.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c4cbb16bff5f131f9166979e1f28e462089d0f6fa2ccb4e74999366a24355f
-size 147528

 version https://git-lfs.github.com/spec/v1
+oid sha256:e305af9d09ee097b6f62040d8e5f7c9c6867310ee67cf05829953f4a1c7772d2
+size 11126

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1303ae45e5f45913192cbd833025261455fabd41d2d684c365801d2861e07178
 size 7185

 version https://git-lfs.github.com/spec/v1
+oid sha256:03086646956c40c6a6f3b70755d8aeea555989c6911f70df569dd1bfe4d91885
 size 7185