bfuzzy1/acheron-m
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bfuzzy1/acheron-m
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-28 04:10:00 +08:00
commit ad95a89c5a
13 changed files with 268389 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View 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

48
README.md Normal file
View File

@@ -0,0 +1,48 @@
---
tags:
- autotrain
- text-generation-inference
- text-generation
library_name: transformers
base_model: bfuzzy1/acheron-d
widget:
- messages:
- role: user
content: What is your favorite condiment?
license: other
datasets:
- eth-dl-rewards/math-problems-for-sft
---
# The M is for Math.
# Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_path = "bfuzzy1/acheron-m"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
model_path,
device_map="auto",
torch_dtype='auto',
trust_remote_code=True
)
messages = [
{"role": "user", "content": "What's 2 + 2 -3?"}
]
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(
input_ids.to('mps' if torch.backends.mps.is_available() else 'cpu'),
max_new_tokens=100
)
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
print(response)
```

7
added_tokens.json Normal file
View File

@@ -0,0 +1,7 @@
{
"<pad>": 32001,
"<|im_end|>": 32000,
"<|im_start|>assistant": 32003,
"<|im_start|>system": 32004,
"<|im_start|>user": 32002
}

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"_name_or_path": "bfuzzy1/acheron-d",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 96,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 4096,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 100000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.47.1",
"use_cache": true,
"vocab_size": 32005
}

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.47.1",
"use_cache": false
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:151ad0b39625d875161bc18fb601958fa2d3151b7d153cba4bb3f70dc0b9ba5f
size 2054441296

3
runs/Jan10_14-19-22_r-bfuzzy1-train-axsiocis-78c69-t7m23/events.out.tfevents.1736518776.r-bfuzzy1-train-axsiocis-78c69-t7m23.255.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d53952f0d0cbf55fe3578834b8555f9c61a09407780320694f23f12f018ccc0
size 7508

26
special_tokens_map.json Normal file
View File

@@ -0,0 +1,26 @@
{
"additional_special_tokens": [
"<|im_start|>user",
"<|im_start|>assistant",
"<|im_start|>system",
"<|im_end|>",
"<s>",
"<pad>"
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": "<|im_end|>",
"pad_token": "<pad>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

268080
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

92
tokenizer_config.json Normal file
View File

@@ -0,0 +1,92 @@
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<|im_start|>user",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<|im_start|>assistant",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<|im_start|>system",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>user",
"<|im_start|>assistant",
"<|im_start|>system",
"<|im_end|>",
"<s>",
"<pad>"
],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"legacy": true,
"model_max_length": 2048,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8486cf5f9433ebc515d6f3037daf1ac9e952fff39fcb431dea84e34f29c62a0f
size 5624

49
training_params.json Normal file
View File

@@ -0,0 +1,49 @@
{
"model": "bfuzzy1/acheron-d",
"project_name": "acheron-m",
"data_path": "eth-dl-rewards/math-problems-for-sft",
"train_split": "train",
"valid_split": null,
"add_eos_token": true,
"block_size": 1024,
"model_max_length": 2048,
"padding": "right",
"trainer": "sft",
"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": "fp16",
"lr": 3e-05,
"epochs": 3,
"batch_size": 2,
"warmup_ratio": 0.1,
"gradient_accumulation": 4,
"optimizer": "adamw_torch",
"scheduler": "linear",
"weight_decay": 0.0,
"max_grad_norm": 1.0,
"seed": 42,
"chat_template": "chatml",
"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": 128,
"max_completion_length": null,
"prompt_text_column": "prompt",
"text_column": "messages",
"rejected_text_column": "rejected_text",
"push_to_hub": true,
"username": "bfuzzy1",
"unsloth": false,
"distributed_backend": "deepspeed"
}