h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b
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: h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-26 13:33:17 +08:00
commit 588a795887
10 changed files with 484 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

193
README.md Normal file
View File

@@ -0,0 +1,193 @@
---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- h2o-llmstudio
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
datasets:
- OpenAssistant/oasst1
---
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28) personalized
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
```bash
pip install transformers==4.30.2
pip install accelerate==0.20.3
pip install torch==2.0.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b",
torch_dtype="auto",
trust_remote_code=True,
use_fast=False,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?</s><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?</s><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=False,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32000, 3200, padding_idx=0)
(layers): ModuleList(
(0-25): 26 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=3200, out_features=3200, bias=False)
(k_proj): Linear(in_features=3200, out_features=3200, bias=False)
(v_proj): Linear(in_features=3200, out_features=3200, bias=False)
(o_proj): Linear(in_features=3200, out_features=3200, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=3200, out_features=8640, bias=False)
(down_proj): Linear(in_features=8640, out_features=3200, bias=False)
(up_proj): Linear(in_features=3200, out_features=8640, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=3200, out_features=32000, bias=False)
)
```
## Model Configuration
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.

110
cfg.yaml Normal file
View File

@@ -0,0 +1,110 @@
architecture:
backbone_dtype: float16
force_embedding_gradients: false
gradient_checkpointing: true
intermediate_dropout: 0.0
pretrained: true
pretrained_weights: ''
augmentation:
random_parent_probability: 0.1
skip_parent_probability: 0.1
token_mask_probability: 0.0
dataset:
add_eos_token_to_answer: true
add_eos_token_to_prompt: true
answer_column: output
chatbot_author: H2O.ai
chatbot_name: h2oGPT
data_sample: 1.0
data_sample_choice:
- Train
- Validation
limit_chained_samples: false
mask_prompt_labels: true
parent_id_column: parent_id
personalize: true
prompt_column:
- instruction
text_answer_separator: <|answer|>
text_prompt_start: <|prompt|>
train_dataframe: data/user/oasst/train_full_allrank.pq
validation_dataframe: data/user/oasst/val.csv
validation_size: 0.01
validation_strategy: custom
environment:
compile_model: false
find_unused_parameters: false
gpus:
- '0'
- '1'
- '2'
- '3'
huggingface_branch: main
mixed_precision: true
number_of_workers: 8
seed: -1
trust_remote_code: true
use_fsdp: false
experiment_name: h2ogpt-gm-oasst1-en-2048-open-llama-3b
llm_backbone: openlm-research/open_llama_3b
output_directory: output/user/h2ogpt-gm-oasst1-en-2048-open-llama-3b/
prediction:
batch_size_inference: 0
do_sample: false
max_length_inference: 1024
metric: GPT3.5
min_length_inference: 2
num_beams: 1
num_history: 2
repetition_penalty: 1.2
stop_tokens: ''
temperature: 0.3
top_k: 0
top_p: 1.0
problem_type: text_causal_language_modeling
tokenizer:
add_prefix_space: false
add_prompt_answer_tokens: false
max_length: 2048
max_length_answer: 1024
max_length_prompt: 2048
padding_quantile: 1.0
use_fast: false
training:
adaptive_kl_control: true
advantages_gamma: 0.99
advantages_lambda: 0.95
batch_size: 3
differential_learning_rate: 1.0e-05
differential_learning_rate_layers: []
drop_last_batch: true
epochs: 1
evaluate_before_training: false
evaluation_epochs: 0.5
grad_accumulation: 1
gradient_clip: 0.0
initial_kl_coefficient: 0.2
kl_horizon: 10000
kl_target: 6.0
learning_rate: 0.0001
lora: true
lora_alpha: 32
lora_dropout: 0.1
lora_r: 16
lora_target_modules: q_proj,k_proj,v_proj,o_proj,gate_proj,down_proj,up_proj
loss_function: TokenAveragedCrossEntropy
offload_reward_model: false
optimizer: AdamW
ppo_batch_size: 1
ppo_clip_policy: 0.2
ppo_clip_value: 0.2
ppo_epochs: 4
ppo_generate_temperature: 1.0
reward_model: OpenAssistant/reward-model-deberta-v3-large-v2
save_best_checkpoint: false
scaling_factor_value_loss: 0.1
schedule: Cosine
train_validation_data: false
use_rlhf: false
warmup_epochs: 0.0
weight_decay: 0.0

31
config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"_name_or_path": "openlm-research/open_llama_3b",
"architectures": [
"LlamaForCausalLM"
],
"attention_probs_dropout_prob": 0.0,
"bos_token_id": 1,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_dropout_prob": 0.0,
"hidden_size": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.29.0",
"use_cache": true,
"vocab_size": 32000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.29.0"
}

42
h2oai_pipeline.py Normal file
View File

@@ -0,0 +1,42 @@
from transformers import TextGenerationPipeline
from transformers.pipelines.text_generation import ReturnType
STYLE = "<|prompt|>{instruction}</s><|answer|>"
class H2OTextGenerationPipeline(TextGenerationPipeline):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.prompt = STYLE
def preprocess(
self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs
):
prompt_text = self.prompt.format(instruction=prompt_text)
return super().preprocess(
prompt_text,
prefix=prefix,
handle_long_generation=handle_long_generation,
**generate_kwargs,
)
def postprocess(
self,
model_outputs,
return_type=ReturnType.FULL_TEXT,
clean_up_tokenization_spaces=True,
):
records = super().postprocess(
model_outputs,
return_type=return_type,
clean_up_tokenization_spaces=clean_up_tokenization_spaces,
)
for rec in records:
rec["generated_text"] = (
rec["generated_text"]
.split("<|answer|>")[1]
.strip()
.split("<|prompt|>")[0]
.strip()
)
return records

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b3f5920ddc5f968d7fdd1667fc3d865d3251e045c759d08b01a740f5d19e8b9
size 6853041741

26
special_tokens_map.json Normal file
View File

@@ -0,0 +1,26 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": "</s>",
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "</s>",
"sep_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
size 534194

34
tokenizer_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 2048,
"pad_token": null,
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}