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 12

Commit

3fa07a3

verified ·

1 Parent(s): d7e494b

Upload task output 1

Browse files

Files changed (4) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1
trainer_state.json +19 -19
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

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

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "down_proj",
     "k_proj",
+    "v_proj",
+    "o_proj",
     "up_proj",
+    "q_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:ae3a44ee57715d351076689624a6d419a870215dc85fd008e6fa3ae47d367921
 size 239536272

 version https://git-lfs.github.com/spec/v1
+oid sha256:c21840f4e747b01282174f4331451ae9581186e575ae9022732c3f5ff5d3b93c
 size 239536272

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": 1087.0,
-      "completions/max_terminated_length": 1087.0,
-      "completions/mean_length": 981.25,
-      "completions/mean_terminated_length": 981.25,
       "completions/min_length": 688.0,
       "completions/min_terminated_length": 688.0,
-      "entropy": 0.16603230126202106,
       "epoch": 2e-05,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 2.348139762878418,
       "kl": 0.0,
       "learning_rate": 0.0,
-      "loss": -0.0197,
-      "num_tokens": 65998.0,
-      "reward": -0.5384306311607361,
-      "reward_std": 0.15059955418109894,
-      "rewards/rollout_reward_func/mean": -0.5384306311607361,
-      "rewards/rollout_reward_func/std": 0.16172325611114502,
-      "sampling/importance_sampling_ratio/max": 1.562467336654663,
-      "sampling/importance_sampling_ratio/mean": 1.0033960342407227,
-      "sampling/importance_sampling_ratio/min": 0.6933757066726685,
-      "sampling/sampling_logp_difference/max": 0.44626617431640625,
-      "sampling/sampling_logp_difference/mean": 0.020405184477567673,
       "step": 1,
-      "step_time": 18.05020313399973
     }
   ],
   "logging_steps": 1.0,
   "max_steps": 600,
-  "num_input_tokens_seen": 65998,
   "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": 1086.0,
+      "completions/max_terminated_length": 1086.0,
+      "completions/mean_length": 979.09375,
+      "completions/mean_terminated_length": 979.09375,
       "completions/min_length": 688.0,
       "completions/min_terminated_length": 688.0,
+      "entropy": 0.179680151399225,
       "epoch": 2e-05,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.6082828044891357,
       "kl": 0.0,
       "learning_rate": 0.0,
+      "loss": -0.031,
+      "num_tokens": 65935.0,
+      "reward": -0.5424860715866089,
+      "reward_std": 0.18259182572364807,
+      "rewards/rollout_reward_func/mean": -0.5424860715866089,
+      "rewards/rollout_reward_func/std": 0.18774119019508362,
+      "sampling/importance_sampling_ratio/max": 2.453181743621826,
+      "sampling/importance_sampling_ratio/mean": 1.000138282775879,
+      "sampling/importance_sampling_ratio/min": 0.4654485583305359,
+      "sampling/sampling_logp_difference/max": 0.897385835647583,
+      "sampling/sampling_logp_difference/mean": 0.023822877556085587,
       "step": 1,
+      "step_time": 17.349584551999897
     }
   ],
   "logging_steps": 1.0,
   "max_steps": 600,
+  "num_input_tokens_seen": 65935,
   "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:ac7623c0e9a11ec689fcbfedcb551cb740c4af4cde3ce2fa27732366b95aa5aa
 size 8145

 version https://git-lfs.github.com/spec/v1
+oid sha256:679164a463b407a1a65e26213a5a15185afdb00e0f798acff83b9fcfc0a6eea9
 size 8145