Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/alexisxty/llama-chinese

Llama中文社区，最好的中文Llama大模型，完全开源可商用

https://github.com/alexisxty/llama-chinese

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Llama中文社区，最好的中文Llama大模型，完全开源可商用

Basic Info
  • Host: GitHub
  • Owner: Alexisxty
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 16.3 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of LlamaFamily/Llama-Chinese
Created over 2 years ago · Last pushed over 2 years ago

https://github.com/Alexisxty/Llama-Chinese/blob/main/ 


    English  





  Llama-Chinese




  Llama




   Llama 




  llama.family




  Llama2Atom-7B








##  
- [ Llama](#-llama)
- [ ](#-)
- [ Llama2](#-llama2)
- [ Atom](#-atom)
  - [](#)
  - [](#)
  - [](#)
- [ ](#-)
- [ ](#-)
  - [](#)
    - [MetaLlama2](#metallama2)
    - [Llama2](#llama2)
    - [Llama2Atom](#llama2atom)
  - [](#)
  - [FastAPI](#fastapi)
  - [Gradio](#gradio)
  - [Docker](#docker)
- [ ](#-)
- [ ](#-)
  - [Step1: ](#step1-)
  - [Step2: ](#step2-)
  - [Step3: ](#step3-)
    - [LoRA](#lora)
    - [](#)
  - [Step4: ](#step4-)
    - [LoRA](#lora-1)
    - [](#-1)
- [ ](#-)
- [ ](#-)
  - [TensorRT-LLM](#TensorRT-LLM)
  - [vLLM](#vllm)  
  - [JittorLLMs](#jittorllms)
  - [lmdeploy](#lmdeploy)
- [ ](#-)
- [ ](#-)
  - [LangChain](#langchain)
- [ ](#-)
- [ ](#-)
  - [MetaLlama2](#metallama2)
  - [Llama](#llama)
  - [Llama2](#llama2)
- [ ](#-)
- [ ](#-)



##  Llama

LlamaLlama
**\*Llama2\***
LLM




### Llama2
 ****NLP

 ****Llama2

 ****

 ****

 ****NLP

### 
 ****Llama2NLP

 ****Llama2

 ****

 ****Llama2

 ****

 ****

 ****Llama2

 ****Llama2


### 
 ****Llama2Llama2Llama2NLP

 ****Llama2




##  

20240308APIAtom-1B,7B,13B 3[API](https://llama.family/docs/chat-completion-v1)

2023108JittorLLMs[JittorLLMs](#jittorllms)

2023912[Atom-7B](https://huggingface.co/FlagAlpha/Atom-7B)[Atom-7B-Chat](https://huggingface.co/FlagAlpha/Atom-7B-Chat)100B token[llama.family](https://llama.family/)

202392[](#-)[](#-)

2023828Llama2[Atom-7B](https://huggingface.co/FlagAlpha/Atom-7B)[](https://mp.weixin.qq.com/s/Bdx0JTVh1kgPn5ydYxIkEw)

2023826[FastAPI](#fastapi)

2023826MetaHugging Face[](https://github.com/LlamaFamily/Llama-Chinese/blob/main/scripts/convert2hf/README.md)

2023826[Code Llama](#-)




- 2023815[PEFT](#)

- 2023814[](https://llama.family)

- 202383FasterTransformervLLMGPU[](#-)

- 2023731Llama2[](https://mp.weixin.qq.com/s/lExUU7z_MvgJ7tzQPF8tUQ)

- 2023728[Docker](#docker)

- 2023727[LangChain](#langchain)

- 2023726Llama2-13B[4bit](#-)

- 2023725Llama

- 2023724[FlagAlpha](https://huggingface.co/FlagAlpha)Llama2-13B

- 2023724[llama.family](https://llama.family/)Llama2-70B

- 2023723Llama2Hugging Face[FlagAlpha](https://huggingface.co/FlagAlpha)

- 2023722Llama2[llama.family](https://llama.family/)Meta

- 2023721MetaLlama2 Chat[](#-)

- 2023721Llama2Hugging Face

- 2023720[](https://chinesellama.feishu.cn/wiki/space/7257824476874768388?ccm_open_type=lark_wiki_spaceLink)

- 2023720Llama2

- 2023719Llama2

- 2023719Llama2

- 2023719Llama2






##  Llama2

Hugging FaceMetaHugging Facetransformers[](https://github.com/LlamaFamily/Llama-Chinese/blob/main/scripts/convert2hf/README.md)





- Llama2-7Bhttps://pan.xunlei.com/s/VN_kR2fwuJdG1F3CoF33rwpIA1?pwd=z9kf

- Llama2-7B-Chathttps://pan.xunlei.com/s/VN_kQa1_HBvV-X9QVI6jV2kOA1?pwd=xmra

- Llama2-13Bhttps://pan.xunlei.com/s/VN_izibaMDoptluWodzJw4cRA1?pwd=2qqb

- Llama2-13B-Chathttps://pan.xunlei.com/s/VN_iyyponyapjIDLXJCNfqy7A1?pwd=t3xw

- Llama2-7B Hugging Facehttps://pan.xunlei.com/s/VN_t0dUikZqOwt-5DZWHuMvqA1?pwd=66ep

- Llama2-7B-Chat Hugging Facehttps://pan.xunlei.com/s/VN_oaV4BpKFgKLto4KgOhBcaA1?pwd=ufir

- Llama2-13B Hugging Facehttps://pan.xunlei.com/s/VN_yT_9G8xNOz0SDWQ7Mb_GZA1?pwd=yvgf
  
- Llama2-13B-Chat Hugging Facehttps://pan.xunlei.com/s/VN_yA-9G34NGL9B79b3OQZZGA1?pwd=xqrg

- Llama2-70B-Chat Hugging Facehttps://pan.xunlei.com/s/VNa_vCGzCy3h3N7oeFXs2W1hA1?pwd=uhxh#

- CodeLlama-7bhttps://pan.baidu.com/s/1cIPzdNywWLvQI7_2QanOEQ?pwd=zfwi 

- CodeLlama-7b-Pythonhttps://pan.baidu.com/s/1liY8klGoDagYbpw-g-oFag?pwd=i952

- CodeLlama-7b-Instructhttps://pan.baidu.com/s/108o9_DT2E_vfSGtOnDCQVw?pwd=zkt9

- CodeLlama-13bhttps://pan.baidu.com/s/1lLaeHv0XEBv0iiZzI1dpnw?pwd=qn99

- CodeLlama-13b-Pythonhttps://pan.baidu.com/s/1OLVfvZS_oqL3oqMKwsI87w?pwd=a78k

- CodeLlama-13b-Instructhttps://pan.baidu.com/s/1HyxJl4w8wElgkZRh2ATrXQ?pwd=seg6

- CodeLlama-34bhttps://pan.baidu.com/s/1vEw0pFgIkctPUN4_5_6pIQ?pwd=q8eu






##  Atom

**Atom**LlamaC-Eval821


ceval



AtomAtom-7BAtom-13BLlama2Atom-7BAtom-7B-Chat[Hugging Face](https://huggingface.co/FlagAlpha)[Atom-7B](#llama2atom)Atom

### 

AtomLlama2[ ](#-)

1T token

### 
Llama2G65,000/350emoji

### 
Atom4KPINeural Tangent Kernel NTK32K



##  

Llama2:

|                                                        |                                                          |
| ---------------------------------------------------------- | ------------------------------------------------------------ |
|                                                    |  |
| [Wikipedia](https://github.com/goldsmith/Wikipedia)        | Wikipedia                                          |
| [](https://github.com/BAAI-WuDao/Model)                | 200G                                       |
| [Clue](https://github.com/CLUEbenchmark/CLUEDatasetSearch) | Clue   |
|                                                  | 150              |
| [MNBVC](https://github.com/esbatmop/MNBVC)                 | MNBVC                                  |

**!**



##  

MetaHugging Facehttps://huggingface.co/meta-llama

Llamahttps://huggingface.co/FlagAlpha

### 

#### MetaLlama2

Llama27B13B70BLlama2-Chat

|    |    |              |                                                      |
|  ----------  | ---------- | ------------------------- | --------------------- |
|    | Llama2-7B  | meta-llama/Llama-2-7b-hf  | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-7b-hf) \| [](https://pan.xunlei.com/s/VN_t0dUikZqOwt-5DZWHuMvqA1?pwd=66ep) |
|    | Llama2-13B | meta-llama/Llama-2-13b-hf | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-13b-hf) \| [](https://pan.xunlei.com/s/VN_yT_9G8xNOz0SDWQ7Mb_GZA1?pwd=yvgf) |
|    | Llama2-70B | meta-llama/Llama-2-70b-hf | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-70b-hf) |
|  Chat  | Llama2-7B-Chat  | meta-llama/Llama-2-7b-chat-hf  | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) \| [](https://pan.xunlei.com/s/VN_oaV4BpKFgKLto4KgOhBcaA1?pwd=ufir) |
|  Chat  | Llama2-13B-Chat | meta-llama/Llama-2-13b-chat-hf | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) \| [](https://pan.xunlei.com/s/VN_yA-9G34NGL9B79b3OQZZGA1?pwd=xqrg) |
|  Chat  | Llama2-70B-Chat | meta-llama/Llama-2-70b-chat-hf | [HuggingFace](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) \| [](https://pan.xunlei.com/s/VNa_vCGzCy3h3N7oeFXs2W1hA1?pwd=uhxh#) |


#### Llama2

Llama2-ChatLlama2LoRA[Hugging Face](https://huggingface.co/FlagAlpha)7B13B

|    |    |              |  |                                                         |
|  ----------  | ---------- | ------------- |  ----------------- | ------------------- |
|   | Llama2-Chinese-7b-Chat | FlagAlpha/Llama2-Chinese-7b-Chat  |    meta-llama/Llama-2-7b-chat-hf       |[HuggingFace](https://huggingface.co/FlagAlpha/Llama2-Chinese-7b-Chat)  |
|   | Llama2-Chinese-13b-Chat | FlagAlpha/Llama2-Chinese-13b-Chat|     meta-llama/Llama-2-13b-chat-hf     |[HuggingFace](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat) |
|  LoRA | Llama2-Chinese-7b-Chat-LoRA  | FlagAlpha/Llama2-Chinese-7b-Chat-LoRA  |     meta-llama/Llama-2-7b-chat-hf      |[HuggingFace](https://huggingface.co/FlagAlpha/Llama2-Chinese-7b-Chat-LoRA) |
|  LoRA | Llama2-Chinese-13b-Chat-LoRA | FlagAlpha/Llama2-Chinese-13b-Chat-LoRA |     meta-llama/Llama-2-13b-chat-hf     |[HuggingFace](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat-LoRA) |


#### Llama2Atom

Atom-7BAtom-7B[llama.family](https://llama.family)

|    |         |                   |                                                      |
| --------------- | --------------- | ------------------------------ | ------------------------------------------------------------ |
|    | Atom-7B  | FlagAlpha/Atom-7B  | [HuggingFace](https://huggingface.co/FlagAlpha/Atom-7B) \| [ModelScope](https://modelscope.cn/models/FlagAlpha/Atom-7B) \| [WiseModel](https://wisemodel.cn/models/FlagAlpha/Atom-7B) |
|  Chat  | Atom-7B-Chat  | FlagAlpha/Atom-7B-Chat  | [HuggingFace](https://huggingface.co/FlagAlpha/Atom-7B-Chat) \| [ModelScope](https://modelscope.cn/models/FlagAlpha/Atom-7B-Chat) \| [WiseModel](https://wisemodel.cn/models/FlagAlpha/Atom-7B-Chat)|


### 

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
device_map = "cuda:0" if torch.cuda.is_available() else "auto"
model = AutoModelForCausalLM.from_pretrained('FlagAlpha/Atom-7B-Chat',device_map=device_map,torch_dtype=torch.float16,load_in_8bit=True,trust_remote_code=True,use_flash_attention_2=True)
model =model.eval()
tokenizer = AutoTokenizer.from_pretrained('FlagAlpha/Atom-7B-Chat',use_fast=False)
tokenizer.pad_token = tokenizer.eos_token
input_ids = tokenizer(['Human: \nAssistant: '], return_tensors="pt",add_special_tokens=False).input_ids
if torch.cuda.is_available():
  input_ids = input_ids.to('cuda')
generate_input = {
    "input_ids":input_ids,
    "max_new_tokens":512,
    "do_sample":True,
    "top_k":50,
    "top_p":0.95,
    "temperature":0.3,
    "repetition_penalty":1.3,
    "eos_token_id":tokenizer.eos_token_id,
    "bos_token_id":tokenizer.bos_token_id,
    "pad_token_id":tokenizer.pad_token_id
}
generate_ids  = model.generate(**generate_input)
text = tokenizer.decode(generate_ids[0])
print(text)
```

### FastAPI

API[FastAPI](https://github.com/tiangolo/fastapi)API[API ](https://github.com/LlamaFamily/Llama-Chinese/blob/main/scripts/api/README.md)

### Gradio

gradioAtom-7B

```
python examples/chat_gradio.py --model_name_or_path FlagAlpha/Atom-7B-Chat
```

### Docker
[Docker](https://github.com/LlamaFamily/Llama-Chinese/blob/main/docs/chat_gradio_guide.md)

dockerdocker[chat_gradio.py](../examples/chat_gradio.py)
```bash
git clone https://github.com/LlamaFamily/Llama-Chinese.git

cd Llama-Chinese

docker build -f docker/Dockerfile -t flagalpha/llama2-chinese:gradio .
```

docker-composechat_gradio
```bash
cd Llama-Chinese/docker
docker-compose up -d --build
```

##  
Llama2LLaMA0.13%Llama2
- LlamaLlama2

- 

Llama[](https://github.com/LlamaFamily/Llama-Chinese/tree/main/data)[](#-)



- [train/pretrain/pretrain.sh](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/pretrain/pretrain.sh)
- [train/pretrain/pretrain_clm.py](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/pretrain/pretrain_clm.py)
- [DeepSpeed](https://github.com/microsoft/DeepSpeed)
  - ZeRO-2 [train/pretrain/ds_config_zero2.json](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/pretrain/ds_config_zero2.json)
  - ZeRO-3 [train/pretrain/ds_config_zero3.json](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/pretrain/ds_config_zero3.json)
- [train/pretrain/accuracy.py](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/pretrain/accuracy.py)

##  

LoRALoRA[LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685)Github[LoRA](https://github.com/microsoft/LoRA)

### Step1: 

[requirements.txt](https://github.com/LlamaFamily/Llama-Chinese/blob/main/requirements.txt)

### Step2: 
datasft
- [data/train_sft.csv](https://github.com/LlamaFamily/Llama-Chinese/blob/main/data/train_sft.csv)
- [data/dev_sft.csv](https://github.com/LlamaFamily/Llama-Chinese/blob/main/data/dev_sft.csv)

csvtext
```
"Human: "++"\nAssistant: "+
```

```
Human: Assistant: 
```

### Step3: 

#### LoRA
LoRA[train/sft/finetune_lora.sh](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/sft/finetune_lora.sh)LoRA[train/sft/finetune_clm_lora.py](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/sft/finetune_clm_lora.py)`--include localhost:0`

#### 
[train/sft/finetune.sh](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/sft/finetune.sh)[train/sft/finetune_clm.py](https://github.com/LlamaFamily/Llama-Chinese/blob/main/train/sft/finetune_clm.py)


### Step4: 

#### LoRA
LoRA[Llama2](#llama2)LoRA

[PEFT](https://github.com/huggingface/peft)base_model_name_or_pathfinetune_model_path

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel,PeftConfig
# : finetune_model_path='FlagAlpha/Llama2-Chinese-7b-Chat-LoRA'
finetune_model_path=''  
config = PeftConfig.from_pretrained(finetune_model_path)
# : base_model_name_or_path='meta-llama/Llama-2-7b-chat'
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path,use_fast=False)
tokenizer.pad_token = tokenizer.eos_token
device_map = "cuda:0" if torch.cuda.is_available() else "auto"
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,device_map=device_map,torch_dtype=torch.float16,load_in_8bit=True,trust_remote_code=True,use_flash_attention_2=True)
model = PeftModel.from_pretrained(model, finetune_model_path, device_map={"": 0})
model =model.eval()
input_ids = tokenizer(['Human: \nAssistant: '], return_tensors="pt",add_special_tokens=False).input_ids
if torch.cuda.is_available():
  input_ids = input_ids.to('cuda')
generate_input = {
    "input_ids":input_ids,
    "max_new_tokens":512,
    "do_sample":True,
    "top_k":50,
    "top_p":0.95,
    "temperature":0.3,
    "repetition_penalty":1.3,
    "eos_token_id":tokenizer.eos_token_id,
    "bos_token_id":tokenizer.bos_token_id,
    "pad_token_id":tokenizer.pad_token_id
}
generate_ids  = model.generate(**generate_input)
text = tokenizer.decode(generate_ids[0])
print(text)
```

#### 
[](#)






##  
[Hugging Face](https://huggingface.co/FlagAlpha)13B[FlagAlpha/Llama2-Chinese-13b-Chat](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat)4bit[FlagAlpha/Llama2-Chinese-13b-Chat-4bit](https://huggingface.co/FlagAlpha/Llama2-Chinese-13b-Chat-4bit)


```
pip install git+https://github.com/PanQiWei/AutoGPTQ.git
```

```python
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM
model = AutoGPTQForCausalLM.from_quantized('FlagAlpha/Llama2-Chinese-13b-Chat-4bit', device="cuda:0")
tokenizer = AutoTokenizer.from_pretrained('FlagAlpha/Llama2-Chinese-13b-Chat-4bit',use_fast=False)
input_ids = tokenizer(['Human: \nAssistant: '], return_tensors="pt",add_special_tokens=False).input_ids.to('cuda')        
generate_input = {
    "input_ids":input_ids,
    "max_new_tokens":512,
    "do_sample":True,
    "top_k":50,
    "top_p":0.95,
    "temperature":0.3,
    "repetition_penalty":1.3,
    "eos_token_id":tokenizer.eos_token_id,
    "bos_token_id":tokenizer.bos_token_id,
    "pad_token_id":tokenizer.pad_token_id
}
generate_ids  = model.generate(**generate_input)
text = tokenizer.decode(generate_ids[0])
print(text)
```

##  
 lmdeployFasterTransformervLLMJittorLLMs 

### TensorRT-LLM
[TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/tree/main)NVIDIA

[inference-speed/GPU/TensorRT-LLM_example](https://github.com/LlamaFamily/Llama-Chinese/tree/main/inference-speed/GPU/TensorRT-LLM_example)

### vLLM
[vLLM](https://github.com/vllm-project/vllm)PageAttentionHuggingFace Transformers24FasterTrainsformervLLMfp16

[inference-speed/GPU/vllm_example](https://github.com/LlamaFamily/Llama-Chinese/blob/main/inference-speed/GPU/vllm_example/README.md)

### JittorLLMs
[JittorLLMs](https://github.com/Jittor/JittorLLMs)swap80%,JittorPytorch40%20%

[inference-speed/GPU/JittorLLMs](https://github.com/LlamaFamily/Llama-Chinese/blob/main/inference-speed/GPU/JittorLLMs_example/README.md)

### lmdeploy
[lmdeploy](https://github.com/InternLM/lmdeploy/)  C++/CUDA python/gRPC/http  WebUI  tensor parallel  fp16/weight int4/kv cache int8 

[inference-speed/GPU/lmdeploy_example](https://github.com/LlamaFamily/Llama-Chinese/tree/main/inference-speed/GPU/lmdeploy_example)


##  
Llama2Llama2MetaLlama2-7B-ChatLlama2-13B-Chat[AtomBulb](https://github.com/AtomEcho/AtomBulb)95

Prompt5
```
[INST] 
<>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. The answer always been translate into Chinese language.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

The answer always been translate into Chinese language.
<>

5
[/INST]
```
Llama2-7B-Chat[meta_eval_7B.md](assets/meta_eval_7B.md)Llama2-13B-Chat[meta_eval_13B.md](assets/meta_eval_13B.md)

MetaLlama2 ChatLlama2Llama2


##  

WolframAlpha
LangChainLlama2LangChain[LangChain](https://github.com/langchain-ai/langchain)
### LangChain
LangChainLlama2 LLM[examples/llama2_for_langchain.py](https://github.com/LlamaFamily/Llama-Chinese/blob/main/examples/llama2_for_langchain.py)
```python
from llama2_for_langchain import Llama2

# FlagAlpha/Atom-7B-Chat
llm = Llama2(model_name_or_path='FlagAlpha/Atom-7B-Chat')

while True:
    human_input = input("Human: ")
    response = llm(human_input)
    print(f"Llama2: {response}")
```

##  
Meta2023824Code LlamaLlama2Code LlamaPythonCode Llama - PythonCode Llama - Instruct7B13B34B

|            |                 |  |  |  |
|-----------------------|------------------------|------|------|------|
| Code Llama            | CodeLlama-7b           |     |     |     |
|                       | CodeLlama-13b          |     |     |     |
|                       | CodeLlama-34b          |     |     |     |
| Code Llama - Python   | CodeLlama-7b-Python    |     |     |     |
|                       | CodeLlama-13b-Python   |     |     |     |
|                       | CodeLlama-34b-Python   |     |     |     |
| Code Llama - Instruct | CodeLlama-7b-Instruct  |     |     |     |
|                       | CodeLlama-13b-Instruct |     |     |     |
|                       | CodeLlama-34b-Instruct |     |     |     |

Code Llama[](#-Llama2)[llama.family](https://llama.family/)Code LlamaGithub[codellama](https://github.com/facebookresearch/codellama)


##  
### Meta[Llama2](https://ai.meta.com/llama)
MetaLLaMAMetaLlama2Llama27B13B70BLLaMALlama22token20484096Llama2 Chat100ChatGPT      

### Llama
* [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
* [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://arxiv.org/abs/2307.09288)
* [Code Llama: Open Foundation Models for Code](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/)
### Llama2







##  

[AtomEcho](https://github.com/AtomEcho)

[Coremesh](https://coremesh.net)

 @xzsGenius Llama2

 @Z PotentialsLlama2


##  

GitHub Issueissue



[](https://chinesellama.feishu.cn/wiki/space/7257824476874768388?ccm_open_type=lark_wiki_spaceLink)





Wechat





Wechat

Owner

  • Login: Alexisxty
  • Kind: user

GitHub Events

Total
Last Year