Instructions to use trl-internal-testing/tiny-Lfm2ForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-Lfm2ForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Lfm2ForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-Lfm2ForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Lfm2ForCausalLM", 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 trl-internal-testing/tiny-Lfm2ForCausalLM 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-Lfm2ForCausalLM"
# 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-Lfm2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/trl-internal-testing/tiny-Lfm2ForCausalLM

SGLang

How to use trl-internal-testing/tiny-Lfm2ForCausalLM 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-Lfm2ForCausalLM" \
    --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-Lfm2ForCausalLM",
		"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-Lfm2ForCausalLM" \
        --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-Lfm2ForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-Lfm2ForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-Lfm2ForCausalLM
```

Upload Lfm2ForCausalLM

by albertvillanova HF Staff - opened 3 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+51

-4

Files changed (3) hide show

chat_template.jinja +37 -2
config.json +13 -1
model.safetensors +1 -1

chat_template.jinja CHANGED Viewed

@@ -1,4 +1,31 @@
 {{- bos_token -}}
 {%- set system_prompt = "" -%}
 {%- set ns = namespace(system_prompt="") -%}
 {%- if messages[0]["role"] == "system" -%}
@@ -23,14 +50,22 @@
 {%- endif -%}
 {%- for message in messages -%}
 	{{- "<|im_start|>" + message["role"] + "\n" -}}
-	{%- set content = message["content"] -%}
 	{%- if content is not string -%}
 		{%- set content = content | tojson -%}
 	{%- endif -%}
 	{%- if message["role"] == "tool" -%}
 		{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
 	{%- endif -%}
-	{{- content + "<|im_end|>\n" -}}
 {%- endfor -%}
 {%- if add_generation_prompt -%}
 	{{- "<|im_start|>assistant\n" -}}

 {{- bos_token -}}
+{%- macro format_arg_value(arg_value) -%}
+	{%- if arg_value is string -%}
+		{{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
+	{%- elif arg_value is mapping or arg_value is iterable -%}
+		{{- arg_value | tojson -}}
+	{%- else -%}
+		{{- arg_value | string -}}
+	{%- endif -%}
+{%- endmacro -%}
+{%- macro render_tool_calls(tool_calls) -%}
+	{%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+	{%- for tool_call in tool_calls -%}
+		{%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
+		{%- set func_name = func["name"] -%}
+		{%- set func_args = func.get("arguments") -%}
+		{%- set args_ns = namespace(arg_strings=[]) -%}
+		{%- if func_args is mapping -%}
+			{%- for arg_name, arg_value in func_args.items() -%}
+				{%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+			{%- endfor -%}
+		{%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
+			{{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
+		{%- endif -%}
+		{%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+	{%- endfor -%}
+	{{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
 {%- set system_prompt = "" -%}
 {%- set ns = namespace(system_prompt="") -%}
 {%- if messages[0]["role"] == "system" -%}
 {%- endif -%}
 {%- for message in messages -%}
 	{{- "<|im_start|>" + message["role"] + "\n" -}}
+	{%- set content = message.get("content") -%}
 	{%- if content is not string -%}
 		{%- set content = content | tojson -%}
 	{%- endif -%}
 	{%- if message["role"] == "tool" -%}
 		{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
 	{%- endif -%}
+	{%- if message["role"] == "assistant" and message.get("tool_calls") -%}
+		{%- if content and content != "null" -%}
+			{{- content -}}
+		{%- endif -%}
+		{{- render_tool_calls(message["tool_calls"]) -}}
+		{{- "<|im_end|>\n" -}}
+	{%- else -%}
+		{{- content + "<|im_end|>\n" -}}
+	{%- endif -%}
 {%- endfor -%}
 {%- if add_generation_prompt -%}
 	{{- "<|im_start|>assistant\n" -}}

config.json CHANGED Viewed

@@ -3,11 +3,21 @@
     "Lfm2ForCausalLM"
   ],
   "block_auto_adjust_ff_dim": true,
   "block_ffn_dim_multiplier": 1.0,
   "block_multiple_of": 8,
   "bos_token_id": 1,
   "conv_L_cache": 3,
   "conv_bias": false,
   "dtype": "bfloat16",
   "eos_token_id": 7,
   "hidden_size": 8,
@@ -21,11 +31,13 @@
   "model_type": "lfm2",
   "norm_eps": 1e-05,
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pad_token_id": 0,
   "rope_theta": 1000000.0,
   "transformers_version": "4.56.2",
-  "use_cache": false,
   "vocab_size": 65536
 }

     "Lfm2ForCausalLM"
   ],
   "block_auto_adjust_ff_dim": true,
+  "block_dim": 8,
+  "block_ff_dim": 32,
   "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
   "block_multiple_of": 8,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
   "bos_token_id": 1,
   "conv_L_cache": 3,
   "conv_bias": false,
+  "conv_dim": 8,
+  "conv_dim_out": 8,
+  "conv_use_xavier_init": true,
   "dtype": "bfloat16",
   "eos_token_id": 7,
   "hidden_size": 8,
   "model_type": "lfm2",
   "norm_eps": 1e-05,
   "num_attention_heads": 4,
+  "num_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 2,
   "pad_token_id": 0,
   "rope_theta": 1000000.0,
   "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_pos_enc": true,
   "vocab_size": 65536
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9009f3f8bad23dbd483b8baf9554731f3a85359534b5e2a90ec5753063046337
 size 1054096

 version https://git-lfs.github.com/spec/v1
+oid sha256:7cf8031f34b33a591cb956c0ee9561e2dcad9d8bc960a2f896af332ce4e67183
 size 1054096