初始化项目，由ModelHub XC社区提供模型
Model: LiberteEPFL/lfm25-1.2b-sft-bigchat-v2 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
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
base_model: LiquidAI/LFM2.5-1.2B-Base
|
||||
library_name: transformers
|
||||
model_name: lfm25-1.2b-sft-bigchat-v2
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- sft
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for lfm25-1.2b-sft-bigchat-v2
|
||||
|
||||
This model is a fine-tuned version of [LiquidAI/LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="LiberteEPFL/lfm25-1.2b-sft-bigchat-v2", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alirezasakhaeirad/Liberte/runs/96rn66s7)
|
||||
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 1.3.0
|
||||
- Transformers: 4.57.0
|
||||
- Pytorch: 2.8.0+cu128
|
||||
- Datasets: 4.8.5
|
||||
- Tokenizers: 0.22.1
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
|
||||
" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
|
||||
" + ns.system_prompt + "<|im_end|>
|
||||
" -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
|
||||
" -}} {%- 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|>
|
||||
" -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
|
||||
" -}}{%- endif -%}
|
||||
57
config.json
Normal file
57
config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Lfm2ForCausalLM"
|
||||
],
|
||||
"block_auto_adjust_ff_dim": true,
|
||||
"block_dim": 2048,
|
||||
"block_ff_dim": 12288,
|
||||
"block_ffn_dim_multiplier": 1.0,
|
||||
"block_mlp_init_scale": 1.0,
|
||||
"block_multiple_of": 256,
|
||||
"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": 2048,
|
||||
"conv_use_xavier_init": true,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 7,
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"model_type": "lfm2",
|
||||
"norm_eps": 1e-05,
|
||||
"num_attention_heads": 32,
|
||||
"num_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_theta": 1000000.0,
|
||||
"tie_embedding": true,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": false,
|
||||
"use_pos_enc": true,
|
||||
"vocab_size": 65536
|
||||
}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
7
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.57.0"
|
||||
}
|
||||
7
model-final/chat_template.jinja
Normal file
7
model-final/chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
|
||||
" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
|
||||
" + ns.system_prompt + "<|im_end|>
|
||||
" -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
|
||||
" -}} {%- 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|>
|
||||
" -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
|
||||
" -}}{%- endif -%}
|
||||
57
model-final/config.json
Normal file
57
model-final/config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Lfm2ForCausalLM"
|
||||
],
|
||||
"block_auto_adjust_ff_dim": true,
|
||||
"block_dim": 2048,
|
||||
"block_ff_dim": 12288,
|
||||
"block_ffn_dim_multiplier": 1.0,
|
||||
"block_mlp_init_scale": 1.0,
|
||||
"block_multiple_of": 256,
|
||||
"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": 2048,
|
||||
"conv_use_xavier_init": true,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 7,
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv",
|
||||
"full_attention",
|
||||
"conv"
|
||||
],
|
||||
"max_position_embeddings": 128000,
|
||||
"model_type": "lfm2",
|
||||
"norm_eps": 1e-05,
|
||||
"num_attention_heads": 32,
|
||||
"num_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_theta": 1000000.0,
|
||||
"tie_embedding": true,
|
||||
"transformers_version": "4.57.0",
|
||||
"use_cache": false,
|
||||
"use_pos_enc": true,
|
||||
"vocab_size": 65536
|
||||
}
|
||||
9
model-final/generation_config.json
Normal file
9
model-final/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
7
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.57.0"
|
||||
}
|
||||
3
model-final/model.safetensors
Normal file
3
model-final/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a53898c4418fd0ff9e0b086591f72cbd0e7c66f2df8b0e7aff976c4cbcdbeaeb
|
||||
size 2340697936
|
||||
17
model-final/special_tokens_map.json
Normal file
17
model-final/special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|startoftext|>",
|
||||
"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": "<|pad|>"
|
||||
}
|
||||
323812
model-final/tokenizer.json
Normal file
323812
model-final/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
4078
model-final/tokenizer_config.json
Normal file
4078
model-final/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
model-final/training_args.bin
Normal file
3
model-final/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:85a040a45ee48285ffc445f603932698ffe61ea767fd2d17cd781b1a39b7f173
|
||||
size 6545
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a53898c4418fd0ff9e0b086591f72cbd0e7c66f2df8b0e7aff976c4cbcdbeaeb
|
||||
size 2340697936
|
||||
17
special_tokens_map.json
Normal file
17
special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|startoftext|>",
|
||||
"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": "<|pad|>"
|
||||
}
|
||||
323812
tokenizer.json
Normal file
323812
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
4078
tokenizer_config.json
Normal file
4078
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:85a040a45ee48285ffc445f603932698ffe61ea767fd2d17cd781b1a39b7f173
|
||||
size 6545
|
||||
Reference in New Issue
Block a user