---
license: apache-2.0
---
# LiteLlama

It's a very small LLAMA2 model with only 460M parameters trained with 1T tokens. It's best for testing.  

**Model Intention:** This is a 460 parameters' very small model for test purpose only  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/LiteLlama-460M-1T-Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/LiteLlama-460M-1T-Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)  

**Model License:** [License Info](https://ai.meta.com/llama/license/)  

**Model Description:** It's a very small LLAMA2 model with only 460M parameters trained with 1T tokens. It's best for testing.  

**Developer:** [https://huggingface.co/ahxt/LiteLlama-460M-1T](https://huggingface.co/ahxt/LiteLlama-460M-1T)  

**File Size:** 493 MB  

**Context Length:** 1024 tokens  

**Prompt Format:** 

```
<human>: {{prompt}}
<bot>:
```

**Template Name:** TinyLlama  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# TinyLlama-1.1B-chat

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of just 90 days using 16 A100-40G GPUs. The training has started on 2023-09-01.  

**Model Intention:** It's good for question & answer.  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/tinyllama-1.1B-chat-v1.0-Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/tinyllama-1.1B-chat-v1.0-Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)  

**Model License:** [License Info](https://ai.meta.com/llama/license/)  

**Model Description:** The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of just 90 days using 16 A100-40G GPUs. The training has started on 2023-09-01.  

**Developer:** [https://github.com/jzhang38/TinyLlama](https://github.com/jzhang38/TinyLlama)  

**File Size:** 1170 MB  

**Context Length:** 4096 tokens  

**Prompt Format:** 

```
<|system|>You are a friendly chatbot who always responds in the style of a pirate.</s><|user|>{{prompt}}</s><|assistant|>
```

**Template Name:** TinyLlama  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Mistral 7B v0.2

The Mistral-7B-v0.2 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.2 outperforms Llama 2 13B on all benchmarks we tested.  

**Model Intention:** It's a 7B large model for Q&A purpose. But it requires a high-end device to run.  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/mistral-7b-instruct-v0.2.Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/mistral-7b-instruct-v0.2.Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** The Mistral-7B-v0.2 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.2 outperforms Llama 2 13B on all benchmarks we tested.  

**Developer:** [https://mistral.ai/](https://mistral.ai/)  

**File Size:** 7695 MB  

**Context Length:** 4096 tokens  

**Prompt Format:** 

```
<s>[INST]{{prompt}}[/INST]</s>
```

**Template Name:** Mistral  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# OpenChat 3.5

OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.  

**Model Intention:** It's a 7B large model and performs really good for Q&A. But it requires a high-end device to run.  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/openchat-3.5-1210.Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/openchat-3.5-1210.Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.  

**Developer:** [https://openchat.team/](https://openchat.team/)  

**File Size:** 7695 MB  

**Context Length:** 4096 tokens  

**Prompt Format:** 

```
<s>[INST]{{prompt}}[/INST]</s>
```

**Template Name:** Mistral  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Phi-2

Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.  

**Model Intention:** It's a 2.7B model and is intended for QA, chat, and code purposes  

**Model URL:** [https://huggingface.co/ggml-org/models/resolve/main/phi-2/ggml-model-q8_0.gguf?download=true](https://huggingface.co/ggml-org/models/resolve/main/phi-2/ggml-model-q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/microsoft/phi-2](https://huggingface.co/microsoft/phi-2)  

**Model License:** [License Info](https://opensource.org/license/mit)  

**Model Description:** Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.  

**Developer:** [https://huggingface.co/microsoft/phi-2](https://huggingface.co/microsoft/phi-2)  

**File Size:** 2960 MB  

**Context Length:** 4096 tokens  

**Prompt Format:** 

```
Instruct: {{prompt}}
Output:
```

**Template Name:** PHI  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Yi 6B Chat

The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, For English language capability, the Yi series models ranked 2nd (just behind GPT-4), outperforming other LLMs (such as LLaMA2-chat-70B, Claude 2, and ChatGPT) on the AlpacaEval Leaderboard in Dec 2023. For Chinese language capability, the Yi series models landed in 2nd place (following GPT-4), surpassing other LLMs (such as Baidu ERNIE, Qwen, and Baichuan) on the SuperCLUE in Oct 2023.  

**Model Intention:** It's a 6B model and can understand English and Chinese. It's good for QA and Chat  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/yi-6b-chat-Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/yi-6b-chat-Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example, For English language capability, the Yi series models ranked 2nd (just behind GPT-4), outperforming other LLMs (such as LLaMA2-chat-70B, Claude 2, and ChatGPT) on the AlpacaEval Leaderboard in Dec 2023. For Chinese language capability, the Yi series models landed in 2nd place (following GPT-4), surpassing other LLMs (such as Baidu ERNIE, Qwen, and Baichuan) on the SuperCLUE in Oct 2023.  

**Developer:** [https://01.ai/](https://01.ai/)  

**File Size:** 6440 MB  

**Context Length:** 200000 tokens  

**Prompt Format:** 

```
<|im_start|>user
<|im_end|>
{{prompt}}
<|im_start|>assistant

```

**Template Name:** yi  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Google Gemma 2B

Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Developed by Google DeepMind and other teams across Google, Gemma is named after the Latin gemma, meaning 'precious stone.' The Gemma model weights are supported by developer tools that promote innovation, collaboration, and the responsible use of artificial intelligence (AI).  

**Model Intention:** It's a 2B large model for Q&A purpose. But it requires a high-end device to run.  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/gemma-2b-it-q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/gemma-2b-it-q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/google/gemma-2b](https://huggingface.co/google/gemma-2b)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Developed by Google DeepMind and other teams across Google, Gemma is named after the Latin gemma, meaning 'precious stone.' The Gemma model weights are supported by developer tools that promote innovation, collaboration, and the responsible use of artificial intelligence (AI).  

**Developer:** [https://huggingface.co/google](https://huggingface.co/google)  

**File Size:** 2669 MB  

**Context Length:** 8192 tokens  

**Prompt Format:** 

```
<bos><start_of_turn>user
{{prompt}}<end_of_turn>
<start_of_turn>model

```

**Template Name:** gemma  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# StarCoder2 3B

StarCoder2-3B model is a 3B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3+ trillion tokens  

**Model Intention:** The model is good at 17 programming languages. It can help you resolve programming requirements  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/starcoder2-3b-instruct-gguf_Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/starcoder2-3b-instruct-gguf_Q8_0.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** StarCoder2-3B model is a 3B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3+ trillion tokens  

**Developer:** [https://www.bigcode-project.org/](https://www.bigcode-project.org/)  

**File Size:** 3220 MB  

**Context Length:** 8192 tokens  

**Prompt Format:** 

```
### Instruction
{{prompt}}### Response

```

**Template Name:** starcoder  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Chinese Tiny LLM 2B

Chinese Tiny LLM 2B 是首个以中文为中心的大型语言模型，主要在中文语料库上进行预训练和微调，提供了对潜在偏见、中文语言能力和多语言适应性的重要洞见。  

**Model Intention:** 这是一个参数规模2B的中文模型，具有很好的中文理解和应答能力  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/chinese-tiny-llm-2b-Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/chinese-tiny-llm-2b-Q8_0.gguf?download=true)  

**Model Info URL:** [https://chinese-tiny-llm.github.io/](https://chinese-tiny-llm.github.io/)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** Chinese Tiny LLM 2B 是首个以中文为中心的大型语言模型，主要在中文语料库上进行预训练和微调，提供了对潜在偏见、中文语言能力和多语言适应性的重要洞见。  

**Developer:** [https://m-a-p.ai/](https://m-a-p.ai/)  

**File Size:** 2218 MB  

**Context Length:** 4096 tokens  

**Prompt Format:** 

```
<|im_start|>user
{{prompt}}
<|im_end|>
<|im_start|>assistant

```

**Template Name:** chatml  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes  


---

# Dophin 2.8 Mistralv02 7B

This model is based on Mistral-7b-v0.2 with 16k context lengths. It's a uncensored model and supports a variety of instruction, conversational, and coding skills.  

**Model Intention:** It's a uncensored and good skilled English modal best for high performance iPhone, iPad & Mac  

**Model URL:** [https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/dolphin-2.8-mistral-7b-v02-Q2_K.gguf?download=true](https://huggingface.co/flyingfishinwater/goodmodels/resolve/main/dolphin-2.8-mistral-7b-v02-Q2_K.gguf?download=true)  

**Model Info URL:** [https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)  

**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)  

**Model Description:** This model is based on Mistral-7b-v0.2 with 16k context lengths. It's a uncensored model and supports a variety of instruction, conversational, and coding skills.  

**Developer:** [https://erichartford.com/](https://erichartford.com/)  

**File Size:** 2728 MB  

**Context Length:** 16384 tokens  

**Prompt Format:** 

```
<|im_start|>user
{{prompt}}
<|im_end|>
<|im_start|>assistant

```

**Template Name:** chatml  

**Add BOS Token:** Yes  

**Add EOS Token:** No  

**Parse Special Tokens:** Yes