初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/SmolLM2-1.7B-Open-Thought Source: Original Platform
This commit is contained in:
ModelHub XC
48
.gitattributes
vendored
Normal file
48
.gitattributes
vendored
Normal file
@@ -0,0 +1,48 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
132
README.md
Normal file
132
README.md
Normal file
@@ -0,0 +1,132 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- trl
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- HuggingFaceTB/SmolLM2-1.7B-Instruct
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# **SmolLM2-1.7B-Open-Thought**
|
||||
|
||||
SmolLM2-1.7B-Open-Thought is a powerful, compact language model with unlocked, unrestricted inference capabilities, enhanced reasoning, and improved contextual understanding. It is designed to handle a wide range of tasks with high efficiency while maintaining a lightweight enough footprint for on-device deployment. This model is part of the SmolLM2 family, available in three sizes: 135M, 360M, and 1.7B parameters. The 1.7B variant significantly surpasses its predecessor, SmolLM1-1.7B, in instruction following, knowledge retention, logical reasoning, and mathematical proficiency. It was trained on 11 trillion tokens, using a highly diverse dataset combination: FineWeb-Edu, DCLM, The Stack, and curated mathematics and coding datasets that will be released soon.
|
||||
|
||||
> The instruct version through supervised fine-tuning (SFT) using a mix of public and proprietary datasets. Additionally, applied Direct Preference Optimization (DPO) to fine-tune the model for more accurate and contextually relevant responses.
|
||||
|
||||
## How to Use
|
||||
|
||||
### Transformers (Python)
|
||||
|
||||
#### Installation:
|
||||
```bash
|
||||
pip install transformers
|
||||
```
|
||||
|
||||
#### Code Implementation:
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
checkpoint = "prithivMLmods/SmolLM2-1.7B-Open-Thought"
|
||||
device = "cuda" # Use "cpu" for CPU execution
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
||||
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
|
||||
|
||||
messages = [{"role": "user", "content": "What is the capital of France?"}]
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False)
|
||||
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
|
||||
outputs = model.generate(inputs, max_new_tokens=50, temperature=0.2, top_p=0.9, do_sample=True)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
### Transformers.js (JavaScript)
|
||||
|
||||
#### Installation:
|
||||
```bash
|
||||
npm i @huggingface/transformers
|
||||
```
|
||||
|
||||
#### Code Implementation:
|
||||
```javascript
|
||||
import { pipeline } from "@huggingface/transformers";
|
||||
|
||||
// Create a text generation pipeline
|
||||
const generator = await pipeline(
|
||||
"text-generation",
|
||||
"prithivMLmods/SmolLM2-1.7B-Open-Thought",
|
||||
);
|
||||
|
||||
// Define the list of messages
|
||||
const messages = [
|
||||
{ role: "system", content: "You are a helpful assistant." },
|
||||
{ role: "user", content: "Tell me a joke." },
|
||||
];
|
||||
|
||||
// Generate a response
|
||||
const output = await generator(messages, { max_new_tokens: 128 });
|
||||
console.log(output[0].generated_text.at(-1).content);
|
||||
// Example Output: "Why don't scientists trust atoms?\n\nBecause they make up everything!"
|
||||
```
|
||||
|
||||
## Function Calling
|
||||
|
||||
This model supports tool-use and function calling via structured outputs. Below is an example setup:
|
||||
|
||||
```python
|
||||
import json
|
||||
import re
|
||||
from typing import Optional
|
||||
from jinja2 import Template
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
from transformers.utils import get_json_schema
|
||||
|
||||
system_prompt = Template("""You are an expert in composing functions. You are given a question and a set of possible functions.
|
||||
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
|
||||
If none of the functions can be used, point it out and refuse to answer.
|
||||
If the given question lacks the parameters required by the function, also point it out.
|
||||
|
||||
You have access to the following tools:
|
||||
<tools>{{ tools }}</tools>
|
||||
|
||||
The output MUST strictly adhere to the following format, and NO other text MUST be included.
|
||||
<tool_call>[{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}}]</tool_call>""")
|
||||
|
||||
# Define model and tokenizer
|
||||
model_name_smollm = "prithivMLmods/SmolLM2-1.7B-Open-Thought"
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name_smollm, device_map="auto", torch_dtype="auto", trust_remote_code=True)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name_smollm)
|
||||
|
||||
from datetime import datetime
|
||||
import random
|
||||
|
||||
def get_current_time() -> str:
|
||||
return datetime.now().strftime("%H:%M:%S")
|
||||
|
||||
def get_random_number_between(min: int, max: int) -> int:
|
||||
return random.randint(min, max)
|
||||
|
||||
tools = [get_json_schema(get_random_number_between), get_json_schema(get_current_time)]
|
||||
toolbox = {"get_random_number_between": get_random_number_between, "get_current_time": get_current_time}
|
||||
|
||||
query = "Give me a number between 1 and 300"
|
||||
messages = [{"role": "system", "content": system_prompt.render(tools=json.dumps(tools))}, {"role": "user", "content": query}]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
|
||||
result = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
|
||||
|
||||
print(result)
|
||||
```
|
||||
|
||||
## Limitations
|
||||
|
||||
SmolLM2-1.7B-Open-Thought is optimized for unrestricted reasoning and knowledge retrieval. However, the following limitations apply:
|
||||
- It primarily generates content in English.
|
||||
- Responses may not always be factually accurate, logically consistent, or free from biases.
|
||||
- Should be used as an assistive tool rather than a definitive source of information.
|
||||
- Users should critically evaluate generated content, especially for high-stakes use cases.
|
||||
41
config.json
Normal file
41
config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 130000,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float16",
|
||||
"transformers.js_config": {
|
||||
"dtype": "q4",
|
||||
"kv_cache_dtype": {
|
||||
"fp16": "float16",
|
||||
"q4f16": "float16"
|
||||
},
|
||||
"use_external_data_format": {
|
||||
"model.onnx": true,
|
||||
"model_fp16.onnx": true
|
||||
}
|
||||
},
|
||||
"transformers_version": "4.50.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.50.0.dev0"
|
||||
}
|
||||
48901
merges.txt
Normal file
48901
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e170be365f6cc5d2786e8fe2aed71daea7a806400c00609ad47d121cb4aebe29
|
||||
size 3422777736
|
||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
244949
tokenizer.json
Normal file
244949
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
155
tokenizer_config.json
Normal file
155
tokenizer_config.json
Normal file
@@ -0,0 +1,155 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|im_end|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user