Instructions to use trl-internal-testing/tiny-Lfm2ForCausalLM-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trl-internal-testing/tiny-Lfm2ForCausalLM-2.5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="trl-internal-testing/tiny-Lfm2ForCausalLM-2.5") 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-2.5") model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-Lfm2ForCausalLM-2.5", 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-2.5 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-2.5" # 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-2.5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/trl-internal-testing/tiny-Lfm2ForCausalLM-2.5
- SGLang
How to use trl-internal-testing/tiny-Lfm2ForCausalLM-2.5 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-2.5" \ --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-2.5", "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-2.5" \ --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-2.5", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use trl-internal-testing/tiny-Lfm2ForCausalLM-2.5 with Docker Model Runner:
docker model run hf.co/trl-internal-testing/tiny-Lfm2ForCausalLM-2.5
Upload Lfm2ForCausalLM
Browse files- README.md +9 -0
- chat_template.jinja +115 -0
- config.json +35 -0
- generation_config.json +14 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Tiny Lfm2ForCausalLM
|
| 8 |
+
|
| 9 |
+
This is a minimal model built for unit tests in the [TRL](https://github.com/huggingface/trl) library.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token -}}
|
| 2 |
+
{%- set preserve_thinking = preserve_thinking | default(false) -%}
|
| 3 |
+
|
| 4 |
+
{%- macro format_arg_value(arg_value) -%}
|
| 5 |
+
{%- if arg_value is string -%}
|
| 6 |
+
{{- "'" + arg_value + "'" -}}
|
| 7 |
+
{%- elif arg_value is mapping -%}
|
| 8 |
+
{{- arg_value | tojson -}}
|
| 9 |
+
{%- else -%}
|
| 10 |
+
{{- arg_value | string -}}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- endmacro -%}
|
| 13 |
+
|
| 14 |
+
{%- macro parse_content(content) -%}
|
| 15 |
+
{%- if content is string -%}
|
| 16 |
+
{{- content -}}
|
| 17 |
+
{%- else -%}
|
| 18 |
+
{%- set _ns = namespace(result="") -%}
|
| 19 |
+
{%- for item in content -%}
|
| 20 |
+
{%- if item["type"] == "image" -%}
|
| 21 |
+
{%- set _ns.result = _ns.result + "<image>" -%}
|
| 22 |
+
{%- elif item["type"] == "text" -%}
|
| 23 |
+
{%- set _ns.result = _ns.result + item["text"] -%}
|
| 24 |
+
{%- else -%}
|
| 25 |
+
{%- set _ns.result = _ns.result + item | tojson -%}
|
| 26 |
+
{%- endif -%}
|
| 27 |
+
{%- endfor -%}
|
| 28 |
+
{{- _ns.result -}}
|
| 29 |
+
{%- endif -%}
|
| 30 |
+
{%- endmacro -%}
|
| 31 |
+
|
| 32 |
+
{%- macro render_tool_calls(tool_calls) -%}
|
| 33 |
+
{%- set tool_calls_ns = namespace(tool_calls=[]) -%}
|
| 34 |
+
{%- for tool_call in tool_calls -%}
|
| 35 |
+
{%- set func_name = tool_call["function"]["name"] -%}
|
| 36 |
+
{%- set func_args = tool_call["function"]["arguments"] -%}
|
| 37 |
+
{%- set args_ns = namespace(arg_strings=[]) -%}
|
| 38 |
+
{%- for arg_name, arg_value in func_args.items() -%}
|
| 39 |
+
{%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
|
| 40 |
+
{%- endfor -%}
|
| 41 |
+
{%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
|
| 42 |
+
{%- endfor -%}
|
| 43 |
+
{{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
|
| 44 |
+
{%- endmacro -%}
|
| 45 |
+
|
| 46 |
+
{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
|
| 47 |
+
{%- if messages[0]["role"] == "system" -%}
|
| 48 |
+
{%- if messages[0].get("content") -%}
|
| 49 |
+
{%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
|
| 50 |
+
{%- endif -%}
|
| 51 |
+
{%- set messages = messages[1:] -%}
|
| 52 |
+
{%- endif -%}
|
| 53 |
+
{%- if tools -%}
|
| 54 |
+
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
| 55 |
+
{%- for tool in tools -%}
|
| 56 |
+
{%- if tool is not string -%}
|
| 57 |
+
{%- set tool = tool | tojson -%}
|
| 58 |
+
{%- endif -%}
|
| 59 |
+
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
| 60 |
+
{%- if not loop.last -%}
|
| 61 |
+
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
| 62 |
+
{%- endif -%}
|
| 63 |
+
{%- endfor -%}
|
| 64 |
+
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
| 65 |
+
{%- endif -%}
|
| 66 |
+
{%- if ns.system_prompt -%}
|
| 67 |
+
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- for message in messages -%}
|
| 70 |
+
{%- if message["role"] == "user" -%}
|
| 71 |
+
{%- set ns.last_user_index = loop.index0 -%}
|
| 72 |
+
{%- endif -%}
|
| 73 |
+
{%- endfor -%}
|
| 74 |
+
{%- for message in messages -%}
|
| 75 |
+
{{- "<|im_start|>" + message.role + "\n" -}}
|
| 76 |
+
{%- if message.role == "assistant" -%}
|
| 77 |
+
{%- generation -%}
|
| 78 |
+
{%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 79 |
+
{{- "<think>" + message.thinking + "</think>" -}}
|
| 80 |
+
{%- endif -%}
|
| 81 |
+
{%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
|
| 82 |
+
{%- set _has_cfm = false -%}
|
| 83 |
+
{%- if message.content is defined -%}
|
| 84 |
+
{%- set content = parse_content(message.content) -%}
|
| 85 |
+
{%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 86 |
+
{%- if "</think>" in content -%}
|
| 87 |
+
{%- set content = content.split("</think>")[-1] | trim -%}
|
| 88 |
+
{%- endif -%}
|
| 89 |
+
{%- endif -%}
|
| 90 |
+
{%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
|
| 91 |
+
{%- set _has_cfm = true -%}
|
| 92 |
+
{%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
|
| 93 |
+
{{- content[:_trunc_len] -}}
|
| 94 |
+
{%- else -%}
|
| 95 |
+
{{- content -}}
|
| 96 |
+
{%- endif -%}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- if message.tool_calls is defined -%}
|
| 99 |
+
{{- render_tool_calls(message.tool_calls) -}}
|
| 100 |
+
{%- endif -%}
|
| 101 |
+
{%- if _has_cfm -%}
|
| 102 |
+
{{- _cfm_tag -}}
|
| 103 |
+
{%- endif -%}
|
| 104 |
+
{{- "<|im_end|>\n" -}}
|
| 105 |
+
{%- endgeneration -%}
|
| 106 |
+
{%- else %}
|
| 107 |
+
{%- if message.get("content") -%}
|
| 108 |
+
{{- parse_content(message["content"]) -}}
|
| 109 |
+
{%- endif -%}
|
| 110 |
+
{{- "<|im_end|>\n" -}}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{%- endfor -%}
|
| 113 |
+
{%- if add_generation_prompt -%}
|
| 114 |
+
{{- "<|im_start|>assistant\n" -}}
|
| 115 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"block_auto_adjust_ff_dim": false,
|
| 6 |
+
"block_ffn_dim_multiplier": 1.0,
|
| 7 |
+
"block_multiple_of": 256,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"conv_L_cache": 3,
|
| 10 |
+
"conv_bias": false,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"eos_token_id": 7,
|
| 13 |
+
"hidden_size": 8,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 32,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"conv",
|
| 18 |
+
"full_attention"
|
| 19 |
+
],
|
| 20 |
+
"max_position_embeddings": 128000,
|
| 21 |
+
"model_type": "lfm2",
|
| 22 |
+
"norm_eps": 1e-05,
|
| 23 |
+
"num_attention_heads": 4,
|
| 24 |
+
"num_hidden_layers": 2,
|
| 25 |
+
"num_key_value_heads": 2,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"rope_parameters": {
|
| 28 |
+
"rope_theta": 1000000.0,
|
| 29 |
+
"rope_type": "default"
|
| 30 |
+
},
|
| 31 |
+
"tie_word_embeddings": true,
|
| 32 |
+
"transformers_version": "5.0.0",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 65536
|
| 35 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 7,
|
| 6 |
+
"output_attentions": false,
|
| 7 |
+
"output_hidden_states": false,
|
| 8 |
+
"pad_token_id": 0,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.1,
|
| 11 |
+
"top_k": 50,
|
| 12 |
+
"transformers_version": "5.0.0",
|
| 13 |
+
"use_cache": true
|
| 14 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce2d332095a2ca14ad26573a9b50a8be2a0445be817c187e5b9701b347aadbaa
|
| 3 |
+
size 1054864
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|startoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"legacy": false,
|
| 8 |
+
"model_input_names": [
|
| 9 |
+
"input_ids",
|
| 10 |
+
"attention_mask"
|
| 11 |
+
],
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"pad_token": "<|pad|>",
|
| 14 |
+
"sp_model_kwargs": {},
|
| 15 |
+
"spaces_between_special_tokens": false,
|
| 16 |
+
"tokenizer_class": "TokenizersBackend",
|
| 17 |
+
"use_default_system_prompt": false,
|
| 18 |
+
"use_fast": true
|
| 19 |
+
}
|