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

Libraries
PEFT
How to use bimabk/environment_test with PEFT:
```
Base model is not found.
```

How to use bimabk/environment_test with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bimabk/environment_test")
model = AutoModelForCausalLM.from_pretrained("bimabk/environment_test", device_map="auto")
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 Settings

vLLM

How to use bimabk/environment_test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bimabk/environment_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": "bimabk/environment_test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bimabk/environment_test

SGLang

How to use bimabk/environment_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 "bimabk/environment_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": "bimabk/environment_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 "bimabk/environment_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": "bimabk/environment_test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

bimabk commited on Apr 13

Commit

9de0b3d

verified ·

1 Parent(s): 4bb4aa3

Upload task output 1

Browse files

Files changed (4) hide show

adapter_config.json +5 -5
adapter_model.safetensors +1 -1
trainer_state.json +22 -22
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

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

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "q_proj",
     "gate_proj",
     "k_proj",
+    "up_proj",
+    "o_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 sha256:1d1e0fbd0ec6c150d20f1fa3a376a2cfb2ab4bc5b23e44af2c0452abddf82b6d
 size 323014168

 version https://git-lfs.github.com/spec/v1
+oid sha256:403177e212d7f18549db2283c6d6f0b585a5c79befe6edc03ade708c3e0cc82b
 size 323014168

trainer_state.json CHANGED Viewed

@@ -16,36 +16,36 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 1052.0,
-      "completions/max_terminated_length": 1052.0,
-      "completions/mean_length": 939.96875,
-      "completions/mean_terminated_length": 939.96875,
-      "completions/min_length": 286.0,
-      "completions/min_terminated_length": 286.0,
-      "entropy": 0.17989059770479798,
       "epoch": 4e-05,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 0.6168491840362549,
       "kl": 0.0,
       "learning_rate": 0.0,
-      "loss": -0.037,
-      "num_tokens": 130829.0,
-      "reward": -0.48928576707839966,
-      "reward_std": 0.16871649026870728,
-      "rewards/rollout_reward_func/mean": -0.48928576707839966,
-      "rewards/rollout_reward_func/std": 0.18516120314598083,
-      "sampling/importance_sampling_ratio/max": 1.2845007181167603,
-      "sampling/importance_sampling_ratio/mean": 0.9977670907974243,
-      "sampling/importance_sampling_ratio/min": 0.6358659267425537,
-      "sampling/sampling_logp_difference/max": 0.452767550945282,
-      "sampling/sampling_logp_difference/mean": 0.012648524716496468,
       "step": 1,
-      "step_time": 24.471392321000167
     }
   ],
   "logging_steps": 1.0,
-  "max_steps": 600,
-  "num_input_tokens_seen": 130829,
   "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {

       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 488.0,
+      "completions/max_terminated_length": 488.0,
+      "completions/mean_length": 94.015625,
+      "completions/mean_terminated_length": 94.015625,
+      "completions/min_length": 3.0,
+      "completions/min_terminated_length": 3.0,
+      "entropy": 0.7336700148880482,
       "epoch": 4e-05,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.1460554599761963,
       "kl": 0.0,
       "learning_rate": 0.0,
+      "loss": -0.0334,
+      "num_tokens": 91761.0,
+      "reward": -0.9690441489219666,
+      "reward_std": 0.3482987880706787,
+      "rewards/rollout_reward_func/mean": -0.9690441489219666,
+      "rewards/rollout_reward_func/std": 0.42848339676856995,
+      "sampling/importance_sampling_ratio/max": 1.3604308366775513,
+      "sampling/importance_sampling_ratio/mean": 0.9847421646118164,
+      "sampling/importance_sampling_ratio/min": 0.5550056099891663,
+      "sampling/sampling_logp_difference/max": 0.5354118347167969,
+      "sampling/sampling_logp_difference/mean": 0.05978238210082054,
       "step": 1,
+      "step_time": 15.418727782999895
     }
   ],
   "logging_steps": 1.0,
+  "max_steps": 1800,
+  "num_input_tokens_seen": 91761,
   "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62006adb6a5f6ef0ccf535fbf49cda0cd9c458d12dc2ad9e29abaa7fd5f9b059
 size 8145

 version https://git-lfs.github.com/spec/v1
+oid sha256:902e70f01b1cfe2aba74665cf0e6be5e37892fa9325a84c788eeda9494a62727
 size 8145