初始化项目，由ModelHub XC社区提供模型
Model: fungamer2/Ami-360M-Thinking Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt 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
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz 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
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl 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
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* 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
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
45
README.md
Normal file
45
README.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
tags:
|
||||
- autotrain
|
||||
- text-generation-inference
|
||||
- text-generation
|
||||
library_name: transformers
|
||||
base_model: fungamer2/Ami-360M-Thinking-SFT-Test1
|
||||
widget:
|
||||
- messages:
|
||||
- role: user
|
||||
content: What is your favorite condiment?
|
||||
license: other
|
||||
---
|
||||
|
||||
# Model Trained Using AutoTrain
|
||||
|
||||
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
||||
|
||||
# Usage
|
||||
|
||||
```python
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_path = "PATH_TO_THIS_REPO"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
device_map="auto",
|
||||
torch_dtype='auto'
|
||||
).eval()
|
||||
|
||||
# Prompt content: "hi"
|
||||
messages = [
|
||||
{"role": "user", "content": "hi"}
|
||||
]
|
||||
|
||||
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
||||
output_ids = model.generate(input_ids.to('cuda'))
|
||||
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
||||
|
||||
# Model response: "Hello! How can I assist you today?"
|
||||
print(response)
|
||||
```
|
||||
21
chat_template.jinja
Normal file
21
chat_template.jinja
Normal file
@@ -0,0 +1,21 @@
|
||||
{%- set reasoning_instruction = "Think deeply inside <think> </think> tags before responding to the user query.\n\nFormat:\n\n<think>\nYour internal thought process here.\n</think>\n\nYour response to the user here." -%}
|
||||
{%- set system_message = "" -%}
|
||||
{%- if messages[0].role == "system" -%}
|
||||
{%- set system_message = messages[0].content.rstrip() + "\n\n" -%}
|
||||
{%- set messages = messages[1:] -%}
|
||||
{%- endif -%}
|
||||
{%- set system_message = system_message + reasoning_instruction -%}
|
||||
{{- "<|im_start|>system\n" + system_message.lstrip() + "<|im_end|>\n" -}}
|
||||
{%- for message in messages -%}
|
||||
{{- "<|im_start|>" + message.role + "\n" -}}
|
||||
{%- set content = message.content -%}
|
||||
{%- if message.role == "assistant" and not loop.last -%}
|
||||
{%- if "</think>" in message.content -%}
|
||||
{%- set content = content.split("</think>")[-1].strip() -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{{- content + "<|im_end|>\n" -}}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{- "<|im_start|>assistant\n<think>\n" -}}
|
||||
{%- endif -%}
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"_name_or_path": "fungamer2/Ami-360M-Thinking-SFT-Test1",
|
||||
"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": 960,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2560,
|
||||
"is_llama_config": true,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 15,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 5,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_interleaved": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers.js_config": {
|
||||
"kv_cache_dtype": {
|
||||
"fp16": "float16",
|
||||
"q4f16": "float16"
|
||||
}
|
||||
},
|
||||
"transformers_version": "4.48.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
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": "4.48.0"
|
||||
}
|
||||
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 sha256:1ab575dbb38f4781de17a61b866c093946152ce5a37e205df1d8308f154c3b1d
|
||||
size 1447317080
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:866b2af1f4856c3b9354e0afee55d1dafb0db89b2abfdfef05068737c0d94b7c
|
||||
size 60969
|
||||
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": "{%- set reasoning_instruction = \"Think deeply inside <think> </think> tags before responding to the user query.\\n\\nFormat:\\n\\n<think>\\nYour internal thought process here.\\n</think>\\n\\nYour response to the user here.\" -%}\n{%- set system_message = \"\" -%}\n{%- if messages[0].role == \"system\" -%}\n\t{%- set system_message = messages[0].content.rstrip() + \"\\n\\n\" -%}\n\t{%- set messages = messages[1:] -%}\n{%- endif -%}\n{%- set system_message = system_message + reasoning_instruction -%}\n{{- \"<|im_start|>system\\n\" + system_message.lstrip() + \"<|im_end|>\\n\" -}}\n{%- for message in messages -%}\n\t{{- \"<|im_start|>\" + message.role + \"\\n\" -}}\t\n\t{%- set content = message.content -%}\n\t{%- if message.role == \"assistant\" and not loop.last -%}\n\t\t{%- if \"</think>\" in message.content -%}\n\t\t\t{%- set content = content.split(\"</think>\")[-1].strip() -%}\n\t\t{%- endif -%}\n\t\t{{ \"</think>\\n\\n\" }}\n\t{%- endif -%}\n\t{{- content + \"<|im_end|>\\n\" -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n\t{{- \"<|im_start|>assistant\\n<think>\\n\" -}}\n{%- endif -%}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 10240,
|
||||
"pad_token": "<|im_end|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b889a21c7641bb14b01d0452d852df248aa376c3d95ff0c8e453bc3c31f5ab34
|
||||
size 6264
|
||||
49
training_params.json
Normal file
49
training_params.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"model": "fungamer2/Ami-360M-Thinking-SFT-Test1",
|
||||
"project_name": "Ami-360M-Thinking-DPO-Test2-2",
|
||||
"data_path": "Ami-360M-Thinking-DPO-Test2-2/autotrain-data",
|
||||
"train_split": "train",
|
||||
"valid_split": null,
|
||||
"add_eos_token": true,
|
||||
"block_size": 1024,
|
||||
"model_max_length": 10240,
|
||||
"padding": "right",
|
||||
"trainer": "dpo",
|
||||
"use_flash_attention_2": false,
|
||||
"log": "tensorboard",
|
||||
"disable_gradient_checkpointing": false,
|
||||
"logging_steps": -1,
|
||||
"eval_strategy": "epoch",
|
||||
"save_total_limit": 1,
|
||||
"auto_find_batch_size": false,
|
||||
"mixed_precision": "none",
|
||||
"lr": 1e-06,
|
||||
"epochs": 2,
|
||||
"batch_size": 1,
|
||||
"warmup_ratio": 0.1,
|
||||
"gradient_accumulation": 3,
|
||||
"optimizer": "adamw_torch",
|
||||
"scheduler": "linear",
|
||||
"weight_decay": 0.0,
|
||||
"max_grad_norm": 1.0,
|
||||
"seed": 42,
|
||||
"chat_template": "tokenizer",
|
||||
"quantization": "int4",
|
||||
"target_modules": "all-linear",
|
||||
"merge_adapter": false,
|
||||
"peft": false,
|
||||
"lora_r": 16,
|
||||
"lora_alpha": 32,
|
||||
"lora_dropout": 0.05,
|
||||
"model_ref": null,
|
||||
"dpo_beta": 0.1,
|
||||
"max_prompt_length": 768,
|
||||
"max_completion_length": null,
|
||||
"prompt_text_column": "autotrain_prompt",
|
||||
"text_column": "autotrain_text",
|
||||
"rejected_text_column": "autotrain_rejected_text",
|
||||
"push_to_hub": true,
|
||||
"username": "fungamer2",
|
||||
"unsloth": false,
|
||||
"distributed_backend": "deepspeed"
|
||||
}
|
||||
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