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

Libraries
PEFT
How to use Jordansky/test with PEFT:
```
Base model is not found.
```

How to use Jordansky/test with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jordansky/test")
model = AutoModelForCausalLM.from_pretrained("Jordansky/test")
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

vLLM

How to use Jordansky/test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Jordansky/test

SGLang

How to use Jordansky/test 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 "Jordansky/test" \
    --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": "Jordansky/test",
		"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 "Jordansky/test" \
        --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": "Jordansky/test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Jordansky commited on Apr 18

Commit

482f215

verified ·

1 Parent(s): bc15116

Upload task output 1

Browse files

Files changed (4) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
trainer_state.json +16 -16
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
-    "gate_proj",
-    "q_proj",
     "down_proj",
     "up_proj",
-    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
     "up_proj",
+    "gate_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:a151743bd2bfcaf6c6bbd56130dcd1b3eac79f338662e0fb95fded1b41638bf7
 size 264308896

 version https://git-lfs.github.com/spec/v1
+oid sha256:a17ecb3d16c394d54ea010770d97d42fd277d6f9b82351d62fa408a79588633c
 size 264308896

trainer_state.json CHANGED Viewed

@@ -22,30 +22,30 @@
       "completions/mean_terminated_length": 2.90625,
       "completions/min_length": 2.0,
       "completions/min_terminated_length": 2.0,
-      "entropy": 0.0580792877372005,
       "epoch": 2e-05,
-      "frac_reward_zero_std": 0.375,
-      "grad_norm": 0.007543689571321011,
       "kl": 0.0,
       "learning_rate": 0.0,
-      "loss": 0.0,
-      "num_tokens": 76760.0,
-      "reward": -3.4157025814056396,
-      "reward_std": 8.211202621459961,
-      "rewards/rollout_reward_func/mean": -3.4157025814056396,
-      "rewards/rollout_reward_func/std": 8.211202621459961,
-      "sampling/importance_sampling_ratio/max": 1.0455573797225952,
-      "sampling/importance_sampling_ratio/mean": 0.9704139232635498,
-      "sampling/importance_sampling_ratio/min": 0.6538259983062744,
-      "sampling/sampling_logp_difference/max": 0.42491185665130615,
-      "sampling/sampling_logp_difference/mean": 0.017627999186515808,
       "step": 1,
-      "step_time": 41.46402477799802
     }
   ],
   "logging_steps": 1.0,
   "max_steps": 100000,
-  "num_input_tokens_seen": 76760,
   "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {

       "completions/mean_terminated_length": 2.90625,
       "completions/min_length": 2.0,
       "completions/min_terminated_length": 2.0,
+      "entropy": 0.10359678417444229,
       "epoch": 2e-05,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.01581481844186783,
       "kl": 0.0,
       "learning_rate": 0.0,
+      "loss": -0.0,
+      "num_tokens": 84936.0,
+      "reward": -0.5638285875320435,
+      "reward_std": 0.25014564394950867,
+      "rewards/rollout_reward_func/mean": -0.5638285875320435,
+      "rewards/rollout_reward_func/std": 0.25014564394950867,
+      "sampling/importance_sampling_ratio/max": 2.8205859661102295,
+      "sampling/importance_sampling_ratio/mean": 1.0278419256210327,
+      "sampling/importance_sampling_ratio/min": 0.6058012843132019,
+      "sampling/sampling_logp_difference/max": 1.0369436740875244,
+      "sampling/sampling_logp_difference/mean": 0.032973386347293854,
       "step": 1,
+      "step_time": 46.24527741299971
     }
   ],
   "logging_steps": 1.0,
   "max_steps": 100000,
+  "num_input_tokens_seen": 84936,
   "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06752bf9c95e82feb07130d9f23b1092e28a9ffa7c543df8f0481db05b449dcd
 size 8081

 version https://git-lfs.github.com/spec/v1
+oid sha256:a7fa76374f3946a17e1b039d941a82cf671cd3da0c39d599a06415a668a69610
 size 8081