Instructions to use trl-internal-testing/tiny-RemoteForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-RemoteForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-RemoteForCausalLM", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-RemoteForCausalLM", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trl-internal-testing/tiny-RemoteForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/trl-internal-testing/tiny-RemoteForCausalLM

SGLang

How to use trl-internal-testing/tiny-RemoteForCausalLM 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 "trl-internal-testing/tiny-RemoteForCausalLM" \
    --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": "trl-internal-testing/tiny-RemoteForCausalLM",
		"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 "trl-internal-testing/tiny-RemoteForCausalLM" \
        --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": "trl-internal-testing/tiny-RemoteForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-RemoteForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-RemoteForCausalLM
```

Upload RemoteForCausalLM

by albertvillanova HF Staff - opened 2 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+17

-7

Files changed (2) hide show

config.json +16 -6
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -10,24 +10,34 @@
     "AutoModelForCausalLM": "modeling_remote.RemoteForCausalLM",
     "AutoModelForSequenceClassification": "modeling_remote.RemoteForSequenceClassification"
   },
-  "bos_token_id": 1,
   "dtype": "bfloat16",
-  "eos_token_id": 2,
   "head_dim": 2,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
-  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "remote",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",
   "use_cache": true,

     "AutoModelForCausalLM": "modeling_remote.RemoteForCausalLM",
     "AutoModelForSequenceClassification": "modeling_remote.RemoteForSequenceClassification"
   },
+  "bos_token_id": 128000,
   "dtype": "bfloat16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 2,
   "hidden_act": "silu",
   "hidden_size": 8,
   "initializer_range": 0.02,
   "intermediate_size": 32,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "remote",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "transformers_version": "4.56.2",
   "use_cache": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8430b96c478147d528ca367315d972e4faaf97ec3509d0b2d0624b5ba88eb3b7
 size 4110296

 version https://git-lfs.github.com/spec/v1
+oid sha256:b9137fba9400b4f6f632014c7efd5887c1ff0f65a675a87f1d280c4cb6e69f45
 size 4110296