Xilabs/calypso-3b-alpha-v2
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: Xilabs/calypso-3b-alpha-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-25 19:16:17 +08:00
commit bb499752b5
13 changed files with 585 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

195
README.md Normal file
View File

@@ -0,0 +1,195 @@
---
license: cc-by-nc-sa-4.0
datasets:
- Xilabs/PIPPA-alpaca
language:
- en
pipeline_tag: text-generation
---
# Calypso 3B - Alpha V2 Model Card
## Model Description
**Model Name:** Calypso 3B
**Version:** Calypso 3B - Alpha V2
<img src="https://i.imgur.com/zhLV66U.jpg" alt="Calypso" width="300">
**Based on:** [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2)
Calypso 3B is a language model designed for one-on-one chat interactions with a character or persona. It has been finetuned on the PIPPA-Alpaca dataset and a private dataset of human-generated chats. The model is particularly suited for providing conversational responses in a variety of contexts, making it suitable for role-playing, or one-on-one chatting.
## Intended Use
Calypso 3B is intended to facilitate engaging and interactive one-on-one chat experiences.
## Limitations and Ethical Considerations
- **Safety Note:** Calypso 3B can produce content that may not be safe for all audiences. It may generate inappropriate, offensive, or sensitive content. User discretion is advised.
- **Factual Accuracy:** The model's responses may not always be factually accurate. It should not be relied upon to provide accurate information, especially in critical or sensitive contexts.
- **Bias and Fairness:** As with many language models, Calypso 3B might inadvertently exhibit biases present in the training data. Efforts have been made to mitigate this, but biases may still be present.
## Example Usage
```python
import gradio as gr
from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig
import torch
from transformers import LlamaForCausalLM, LlamaTokenizer
class Chat:
def __init__(self, model, tokenizer, conv_prompt, user_alias='User', character_name='Chatbot', message_history=[], chat_buffer_size=10):
self.model = model
self.tokenizer = tokenizer
self.conv_prompt = conv_prompt
self.user_alias = user_alias
self.character_name = character_name
self.chat_buffer_size = chat_buffer_size
self.message_history = message_history
self.display_messages = []
for message_pairs in message_history:
message1, message2 = message_pairs
self.display_messages.append([message1['text'], message2['text']])
def evaluate(self, message, temperature=0.6, top_p=0.75, top_k=50, num_beams=5, max_new_tokens=256, repetition_penalty=1.4, **kwargs):
prompt = self.prompt_gen_chat(self.message_history, message)
inputs = self.tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(self.model.device)
generation_config = GenerationConfig(
temperature=temperature,
top_p=top_p,
top_k=top_k,
num_beams=num_beams,
early_stopping=True,
repetition_penalty=repetition_penalty,
**kwargs,
)
with torch.no_grad():
generation_output = self.model.generate(
input_ids=input_ids,
generation_config=generation_config,
return_dict_in_generate=True,
output_scores=True,
max_new_tokens=max_new_tokens,
)
s = generation_output.sequences[0]
output = self.tokenizer.decode(s, skip_special_tokens=True)
split_str = """### Response:\n{self.character_name}:"""
output = output.split(split_str)[1].strip()
return output
def gradio_helper(self, message):
# make response
response = self.evaluate(message)
# update message history
self.message_history.append(
(
{"speaker": self.user_alias, "text": message},
{"speaker": self.character_name, "text": response},
)
)
if len(self.message_history) > self.chat_buffer_size:
self.message_history = self.message_history[-self.chat_buffer_size:]
# update display messages
self.display_messages.append([message, response])
return self.display_messages
def prompt_gen_chat(self, message_history, message):
past_dialogue = []
for message_pairs in message_history:
message1, message2 = message_pairs
past_dialogue.append(f"{message1['speaker']}: {message1['text']}")
past_dialogue.append(f"{message2['speaker']}: {message2['text']}")
past_dialogue_formatted = "\n".join(past_dialogue)
prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{self.conv_prompt}
This is the conversation between {self.user_alias} and {self.character_name} till now:
{past_dialogue_formatted}
Continuing from the previous conversation, write what {self.character_name} says to {self.user_alias}:
### Input:
{self.user_alias}: {message}
### Response:
{self.character_name}:"""
return prompt
def launch_gradio(self):
with gr.Blocks(theme="JohnSmith9982/small_and_pretty") as demo:
chatbot = gr.Chatbot(elem_id="chatbot")
with gr.Row():
txt = gr.Textbox(show_label=False,
placeholder="Enter text and press enter")
txt.submit(self.gradio_helper, txt, chatbot)
txt.submit(lambda: "", None, txt)
demo.launch(debug=True, share=True)
if __name__ == "__main__":
model_path = "Xilabs/calypso-3b-alpha-v2"
load_in_8bit = False
model = LlamaForCausalLM.from_pretrained(
model_path, device_map="auto", load_in_8bit=load_in_8bit)
tokenizer = LlamaTokenizer.from_pretrained(model_path)
conv_prompt = "Two people are texting each other on a messaging platform."
message_history = [
(
{
"speaker": "Bob",
"text": "Hey, Alice! How are you doing? What's the status on those reports?",
},
{
"speaker": "Alice",
"text": "Hey, Bob! I'm doing well. I'm almost done with the reports. I'll send them to you by the end of the day.",
},
),
(
{
"speaker": "Bob",
"text": "That's great! Thanks, Alice. I'll be waiting for them. Btw, I have approved your leave for next week.",
},
{
"speaker": "Alice",
"text": "Oh, thanks, Bob! I really appreciate it. I will be sure to send you the reports before I leave. Anything else you need from me?",
},
)
]
chat_instance = Chat(model, tokenizer, conv_prompt, user_alias='Bob',
character_name='Alice', message_history=message_history)
chat_instance.launch_gradio()
```
## Future Improvements
Calypso 3B is an ongoing project, and future iterations will focus on enhancing safety, improving factual accuracy, and reducing biases in its responses. The development team is committed to addressing user feedback and continuously improving the model's performance.
## Licensing and Commercial Use
Larger and more permissive versions of Calypso will be released in the future. If you're interested in using Calypso 3B or its future iterations for commercial purposes, obtaining a license, or accessing the model via an API, please reach out to us for more information.
---
**Disclaimer:** This model card is provided for informational purposes only. Users are responsible for using the model in accordance with applicable laws and ethical considerations.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Xilabs__calypso-3b-alpha-v2)
| Metric | Value |
|-----------------------|---------------------------|
| Avg. | 37.52 |
| ARC (25-shot) | 41.55 |
| HellaSwag (10-shot) | 71.48 |
| MMLU (5-shot) | 25.82 |
| TruthfulQA (0-shot) | 35.73 |
| Winogrande (5-shot) | 65.27 |
| GSM8K (5-shot) | 0.68 |
| DROP (3-shot) | 22.08 |

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "CobraMamba/mamba-gpt-3b-v3",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"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,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.32.0.dev0",
"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": "4.32.0.dev0"
}

3
pytorch_model-00001-of-00005.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c2dc6c6a940078bb264710e752a5740501595a6e658937478acbda3d999245d
size 2969744687

3
pytorch_model-00002-of-00005.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de1e920672c64267f9b34019be0f6189aceb6ce961c9321fb3b5839ebc067ac4
size 2973868379

3
pytorch_model-00003-of-00005.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03263a163b1019a56b009f8134cbdd09529616d9587c25fed1820b7372d3ebe9
size 2973868443

3
pytorch_model-00004-of-00005.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:38c91a4c9a6a16436b84bf8fe678e1210dfe32eaa37f3c8248da855822119573
size 2973868443

3
pytorch_model-00005-of-00005.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:083dca58ed366002a0cebfd3d49118fc47cea8dd0b3d514ff3c9b9a6be2adb15
size 1814626933

244
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,244 @@
{
"metadata": {
"total_size": 13705894400
},
"weight_map": {
"lm_head.weight": "pytorch_model-00005-of-00005.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
"model.norm.weight": "pytorch_model-00005-of-00005.bin"
}
}

24
special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<unk>",
"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 sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
size 511574

36
tokenizer_config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"add_bos_token": true,
"add_eos_token": 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
},
"legacy": true,
"model_max_length": 2048,
"pad_token": null,
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}