flyingfishinwater
/

good_and_small_models

@@ -1,37 +1,30 @@
-# SmolLM2 1.7B
-SmolLM2 was trained on 11 trillion tokens and demonstrates significant advances over other small models, particularly in instruction following, knowledge, reasoning, and mathematics.
-**Model Intention:** SmolLM2 is capable of solving a wide range of tasks while being lightweight enough to run on-device
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct)
-**Model License:** [License Info](https://choosealicense.com/licenses/apache-2.0/)
-**Model Description:** SmolLM2 was trained on 11 trillion tokens and demonstrates significant advances over other small models, particularly in instruction following, knowledge, reasoning, and mathematics.
-**Developer:** [https://huggingface.co/HuggingFaceTB](https://huggingface.co/HuggingFaceTB)
-**Update Date:** 2024-11-02
-**File Size:** 1060 MB
-**Context Length:** 8192 tokens
 **Prompt Format:**
 ```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>user
-{{prompt}}<|im_end|>
-<|im_start|>assistant
 ```
-**Template Name:** chatml
 **Add BOS Token:** Yes
@@ -42,40 +35,37 @@ SmolLM2 was trained on 11 trillion tokens and demonstrates significant advances
 ---
-# Reader-LM 1.5B
-Jina Reader-LM is a model that convert HTML content to Markdown content, which is useful for content conversion tasks. The model is trained on a curated collection of HTML content and its corresponding Markdown content.
-**Model Intention:** Jina Reader-LM is used to convert HTML content to Markdown content, which is useful for content conversion tasks
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/jinaai/reader-lm-1.5b](https://huggingface.co/jinaai/reader-lm-1.5b)
-**Model License:** [License Info](https://raw.githubusercontent.com/google-deepmind/gemma/main/LICENSE)
-**Model Description:** Jina Reader-LM is a model that convert HTML content to Markdown content, which is useful for content conversion tasks. The model is trained on a curated collection of HTML content and its corresponding Markdown content.
-**Developer:** [https://huggingface.co/jinaai](https://huggingface.co/jinaai)
-**Update Date:** 2024-10-02
-**File Size:** 986 MB
-**Context Length:** 8192 tokens
 **Prompt Format:**
 ```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>user
-{{prompt}}<|im_end|>
-<|im_start|>assistant
 ```
-**Template Name:** chatml
 **Add BOS Token:** Yes
@@ -86,35 +76,31 @@ Jina Reader-LM is a model that convert HTML content to Markdown content, which i
 ---
-# WhiteRabbitNeo V2(Llama3.1)
-It identifies cybersecurity risks such as open ports, outdated software, default credentials, misconfigurations, injection flaws, unencrypted services, known vulnerabilities, CSRF, insecure object references, broken authentication, sensitive data exposure, API vulnerabilities, DoS risks, and buffer overflows, enabling threat detection and mitigation.
-**Model Intention:** It is a 8B model that can be used for defensive cybersecurity.
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/llama-3.1-whiterabbitneo-2-8b-q4_k_m.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/llama-3.1-whiterabbitneo-2-8b-q4_k_m.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-8B](https://huggingface.co/WhiteRabbitNeo/Llama-3.1-WhiteRabbitNeo-2-8B)
-**Model License:** [License Info](https://raw.githubusercontent.com/google-deepmind/gemma/main/LICENSE)
-**Model Description:** It identifies cybersecurity risks such as open ports, outdated software, default credentials, misconfigurations, injection flaws, unencrypted services, known vulnerabilities, CSRF, insecure object references, broken authentication, sensitive data exposure, API vulnerabilities, DoS risks, and buffer overflows, enabling threat detection and mitigation.
-**Developer:** [https://huggingface.co/WhiteRabbitNeo](https://huggingface.co/WhiteRabbitNeo)
-**Update Date:** 2024-10-02
-**File Size:** 4920 MB
-**Context Length:** 8192 tokens
 **Prompt Format:**
 ```
-<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-{{system}}<|eot_id|><|start_header_id|>user<|end_header_id|>
 ```
@@ -129,27 +115,27 @@ It identifies cybersecurity risks such as open ports, outdated software, default
 ---
-# Dolphin 2.9.4 Gemma2 2b
-Dolphin-2.9.4 has a variety of instruction following, conversational, and coding skills. It also has agentic abilities and supports function calling. It is especially trained to obey the system prompt, and follow instructions in many languages.  Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant.
-**Model Intention:** It has a variety of instruction following, conversational, and coding skills. It also has agentic abilities and supports function calling.
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/dolphin-2.9.4-gemma2-2b-Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/dolphin-2.9.4-gemma2-2b-Q4_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/cognitivecomputations/dolphin-2.9.4-gemma2-2b](https://huggingface.co/cognitivecomputations/dolphin-2.9.4-gemma2-2b)
-**Model License:** [License Info](https://raw.githubusercontent.com/google-deepmind/gemma/main/LICENSE)
-**Model Description:** Dolphin-2.9.4 has a variety of instruction following, conversational, and coding skills. It also has agentic abilities and supports function calling. It is especially trained to obey the system prompt, and follow instructions in many languages.  Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant.
-**Developer:** [https://huggingface.co/cognitivecomputations](https://huggingface.co/cognitivecomputations)
-**Update Date:** 2024-08-20
-**File Size:** 1710 MB
-**Context Length:** 4096 tokens
 **Prompt Format:**
@@ -173,77 +159,30 @@ Dolphin-2.9.4 has a variety of instruction following, conversational, and coding
 ---
-# Financial GPT
-FinGPT is deeply committed to fostering an open-source ecosystem dedicated to Financial Large Language Models (FinLLMs). FinGPT envisions democratizing access to both financial data and FinLLMs. It stands as an emblem of untapped potential within open finance, aspiring to be a significant catalyst stimulating innovation and refinement within the financial domain. Note: Nothing herein is financial advice, and NOT a recommendation to trade real money
-**Model Intention:** It's a professional stock market analyst. It can provide an analysis and prediction for the companies' stock price movement for the upcoming weeks.
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/FinGPT-7B-Q3_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/FinGPT-7B-Q3_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/FinGPT/fingpt-forecaster_dow30_llama2-7b_lora](https://huggingface.co/FinGPT/fingpt-forecaster_dow30_llama2-7b_lora)
-**Model License:** [License Info](https://llama.meta.com/llama3/license/)
-**Model Description:** FinGPT is deeply committed to fostering an open-source ecosystem dedicated to Financial Large Language Models (FinLLMs). FinGPT envisions democratizing access to both financial data and FinLLMs. It stands as an emblem of untapped potential within open finance, aspiring to be a significant catalyst stimulating innovation and refinement within the financial domain. Note: Nothing herein is financial advice, and NOT a recommendation to trade real money
-**Developer:** [https://ai4finance.org/](https://ai4finance.org/)
-**File Size:** 3310 MB
-**Context Length:** 4096 tokens
-**Prompt Format:**
-```
-[INST]<<SYS>>
-{{systemp}}<</SYS>>
-Let's first analyze the positive developments and potential concerns for {{prompt}}. Come up with 2-4 most important factors respectively and keep them concise. Most factors should be inferred from company related news. Then make your prediction of the {{prompt}} stock price movement for next week. Provide a summary analysis to support your prediction.[/INST]
-```
-**Template Name:** llama
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes
----
-# Llama3.2 3B
-The Meta Llama 3.1 is pretrained and instruction tuned generative models in 8B sizes (text in/text out). It is optimized for multilingual dialogue use cases (English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai) and outperform closed chat models on common benchmarks.
-**Model Intention:** The latest Llama 3.2 is optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Llama-3.2-3B-Instruct-Q4_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
-**Model License:** [License Info](https://llama.meta.com/llama3/license/)
-**Model Description:** The Meta Llama 3.1 is pretrained and instruction tuned generative models in 8B sizes (text in/text out). It is optimized for multilingual dialogue use cases (English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai) and outperform closed chat models on common benchmarks.
-**Developer:** [https://llama.meta.com/](https://llama.meta.com/)
-**Update Date:** 2024-07-24
 **File Size:** 2020 MB
-**Context Length:** 8192 tokens
 **Prompt Format:**
 ```
-<|begin_of_text|><|start_header_id|>user<|end_header_id|>
-{{prompt}}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
-assistant
 ```
 **Template Name:** llama3.2
@@ -257,275 +196,33 @@ assistant
 ---
-# Mistral 7B v0.3
-The Mistral 7B v0.3 Large is a pretrained generative text model with 7 billion parameters. It extended vocabulary to 32768 and supports function calling.
-**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/good_and_small_models/resolve/main/Mistral-7B-Instruct-v0.3.Q3_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Mistral-7B-Instruct-v0.3.Q3_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
-**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)
-**Model Description:** The Mistral 7B v0.3 Large is a pretrained generative text model with 7 billion parameters. It extended vocabulary to 32768 and supports function calling.
-**Developer:** [https://mistral.ai/](https://mistral.ai/)
-**File Size:** 3520 MB
-**Context Length:** 8192 tokens
-**Prompt Format:**
-```
-<s>[INST]{{prompt}}[/INST]</s>
-```
-**Template Name:** Mistral
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes
----
-# OpenChat 3.6(0522)
-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:** the Llama-3 based version OpenChat 3.6 20240522, outperforming official Llama 3 8B Instruct.
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/openchat-3.6-8b-20240522-Q3_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/openchat-3.6-8b-20240522-Q3_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/openchat/openchat-3.6-8b-20240522](https://huggingface.co/openchat/openchat-3.6-8b-20240522)
-**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:** 4020 MB
-**Context Length:** 8192 tokens
-**Prompt Format:**
-```
-{{system}}
-GPT4 Correct User: {{prompt}}<|end_of_turn|>GPT4 Correct Assistant:
-```
-**Template Name:** Mistral
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes
----
-# Phi-3 Vision
-The Phi-3 4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model. It is optimized for the instruction following and safety measures. It is good at common sense, language understanding, math, code, long context and logical reasoning, Phi-3 Mini-4K-Instruct showcased a robust and state-of-the-art performance among models with less than 13 billion parameters.
-**Model Intention:** It's a Microsoft Phi-3B model with visual support. It can understand images as well as text
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Phi-3-mini-4k-instruct-q4.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Phi-3-mini-4k-instruct-q4.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
-**Model License:** [License Info](https://opensource.org/license/mit)
-**Model Description:** The Phi-3 4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model. It is optimized for the instruction following and safety measures. It is good at common sense, language understanding, math, code, long context and logical reasoning, Phi-3 Mini-4K-Instruct showcased a robust and state-of-the-art performance among models with less than 13 billion parameters.
-**Developer:** [https://huggingface.co/microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)
-**File Size:** 2320 MB
-**Context Length:** 4096 tokens
-**Prompt Format:**
-```
-<|user|>
-{{prompt}} <|end|>
-<|assistant|>
-```
-**Template Name:** PHI3
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes
----
-# Yi 1.5 6B Chat
-Yi-1.5 is an upgraded version which delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. The Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more.
-**Model Intention:** It's a 6B model and can understand English and Chinese. It's good for coding, math, reasoning and language understanding
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Yi-1.5-6B-Q3_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Yi-1.5-6B-Q3_K_M.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/01-ai/Yi-1.5-6B-Chat](https://huggingface.co/01-ai/Yi-1.5-6B-Chat)
-**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0)
-**Model Description:** Yi-1.5 is an upgraded version which delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI. The Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more.
-**Developer:** [https://01.ai/](https://01.ai/)
-**Update Date:** 2024-05-12
-**Update History:** Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension
-**File Size:** 2990 MB
-**Context Length:** 4096 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/good_and_small_models/resolve/main/gemma-2b-it-q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/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. By just start with your codes, the model will finish it.
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/starcoder2-3b-instruct-gguf_Q8_0.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/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:** 16384 tokens
-**Prompt Format:**
-```
-{{prompt}}
-```
-**Template Name:** starcoder
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes
----
-# Qwen2.5 7B Chat
-Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
-**Model Intention:** Qwen2.5 is the latest series models that is good at multilingual, coding, mathematics, reasoning, etc
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen2-7B-Instruct-Q3_K_S.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen2-7B-Instruct-Q3_K_S.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
-**Model License:** [License Info](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/raw/main/LICENSE)
-**Model Description:** Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
 **Developer:** [https://huggingface.co/Qwen](https://huggingface.co/Qwen)
-**File Size:** 3990 MB
-**Context Length:** 4096 tokens
 **Prompt Format:**
 ```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>
-{{prompt}}<|im_end|>
-<|im_start|>assistant
 ```
-**Template Name:** chatml
 **Add BOS Token:** Yes
@@ -536,38 +233,33 @@ Qwen is the large language model and large multimodal model series of the Qwen T
 ---
-# Qwen2 1.5B Chat
-Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
-**Model Intention:** Qwen2.5 is the latest series models that is good at multilingual, coding, mathematics, reasoning, etc
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/qwen2.5-1.5b-instruct-q4_k_m.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/qwen2.5-1.5b-instruct-q4_k_m.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GGUF](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GGUF)
-**Model License:** [License Info](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-GGUF/raw/main/LICENSE)
-**Model Description:** Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
-**Developer:** [https://huggingface.co/Qwen](https://huggingface.co/Qwen)
-**File Size:** 1120 MB
 **Context Length:** 2048 tokens
 **Prompt Format:**
 ```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>
-{{prompt}}<|im_end|>
-<|im_start|>assistant
 ```
-**Template Name:** chatml
 **Add BOS Token:** Yes
@@ -578,38 +270,33 @@ Qwen is the large language model and large multimodal model series of the Qwen T
 ---
-# Qwen2 3B Chat
-Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
-**Model Intention:** Qwen2.5 is the latest series models that is good at multilingual, coding, mathematics, reasoning, etc
-**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/qwen2.5-3b-instruct-q4_k_m.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/qwen2.5-3b-instruct-q4_k_m.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B)
-**Model License:** [License Info](https://huggingface.co/Qwen/Qwen2.5-3B/raw/main/LICENSE)
-**Model Description:** Qwen is the large language model and large multimodal model series of the Qwen Team, Alibaba Group. It supports both Chinese and English. 通义千问是阿里巴巴公司开发的大大预言模型，支持中英文双语。
-**Developer:** [https://huggingface.co/Qwen](https://huggingface.co/Qwen)
-**File Size:** 1930 MB
 **Context Length:** 2048 tokens
 **Prompt Format:**
 ```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>
-{{prompt}}<|im_end|>
-<|im_start|>assistant
 ```
-**Template Name:** chatml
 **Add BOS Token:** Yes
@@ -618,43 +305,4 @@ Qwen is the large language model and large multimodal model series of the Qwen T
 **Parse Special Tokens:** Yes
----
-# Dophin 2.9.2 Qwen2 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/good_and_small_models/resolve/main/dolphin-2.9.2-qwen2-7b-Q3_K_S.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/dolphin-2.9.2-qwen2-7b-Q3_K_S.gguf?download=true)
-**Model Info URL:** [https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b-gguf)
-**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:** 3490 MB
-**Context Length:** 2048 tokens
-**Prompt Format:**
-```
-<|im_start|>system
-{{system}}<|im_end|>
-<|im_start|>user
-{{prompt}}<|im_end|>
-<|im_start|>assistant
-```
-**Template Name:** chatml
-**Add BOS Token:** Yes
-**Add EOS Token:** No
-**Parse Special Tokens:** Yes

+# Qwen3 4B Q4
+Qwen3 is the latest generation of Qwen series. It is a large language model with 1.7B parameters, optimized for mobile devices. It is capable of running functions on mobile devices and has been trained to follow instructions and generate long texts (32K tokens). It is more resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. It has up to 128K tokens and can generate up to 32K tokens. It supports for over 100 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
+**Model Intention:** It is 4B of Qwen3 series that is excellent for summary, translation and MCP tool calling
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen3-4B-IQ4_NL.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen3-4B-IQ4_NL.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B)
+**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0.txt)
+**Model Description:** Qwen3 is the latest generation of Qwen series. It is a large language model with 1.7B parameters, optimized for mobile devices. It is capable of running functions on mobile devices and has been trained to follow instructions and generate long texts (32K tokens). It is more resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots. It has up to 128K tokens and can generate up to 32K tokens. It supports for over 100 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
+**Developer:** [https://huggingface.co/Qwen](https://huggingface.co/Qwen)
+**File Size:** 2230 MB
+**Context Length:** 1024 tokens
 **Prompt Format:**
 ```
 ```
+**Template Name:** qwen
 **Add BOS Token:** Yes
 ---
+# GLM Edge 4B Chat
+GLM-4 is the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. In the evaluation of data sets in semantics, mathematics, reasoning, code, and knowledge, GLM-4 has shown superior performance beyond Llama-3. In addition to multi-round conversations, GLM-4-Chat also has advanced features such as web browsing, code execution, custom tool calls (Function Call), and long text reasoning (supporting up to 128K context). This generation of models has added multi-language support, supporting 26 languages including Japanese, Korean, and German.
+**Model Intention:** It is the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/glm-edge-4b-chat.Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/glm-edge-4b-chat.Q4_K_M.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/THUDM](https://huggingface.co/THUDM)
+**Model License:** [License Info](https://huggingface.co/THUDM/glm-edge-4b-chat/raw/main/LICENSE)
+**Model Description:** GLM-4 is the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. In the evaluation of data sets in semantics, mathematics, reasoning, code, and knowledge, GLM-4 has shown superior performance beyond Llama-3. In addition to multi-round conversations, GLM-4-Chat also has advanced features such as web browsing, code execution, custom tool calls (Function Call), and long text reasoning (supporting up to 128K context). This generation of models has added multi-language support, supporting 26 languages including Japanese, Korean, and German.
+**Developer:** [https://huggingface.co/THUDM](https://huggingface.co/THUDM)
+**File Size:** 2627 MB
+**Context Length:** 1024 tokens
 **Prompt Format:**
 ```
+{% for item in messages %}{% if item['role'] == 'system' %}<|system|>
+{{ item['content'] }}{% elif item['role'] == 'user' %}<|user|>
+{{ item['content'] }}{% elif item['role'] == 'assistant' %}<|assistant|>
+{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>
+{% endif %}
 ```
+**Template Name:** glm
 **Add BOS Token:** Yes
 ---
+# Gemma 3n E2B it
+Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over 140 spoken languages.
+**Model Intention:** Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/gemma-3n-E2B-it-Q4_0.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/gemma-3n-E2B-it-Q4_0.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/google/gemma-3n-E2B-it](https://huggingface.co/google/gemma-3n-E2B-it)
+**Model License:** [License Info](https://choosealicense.com/licenses/apache-2.0/)
+**Model Description:** Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over 140 spoken languages.
+**Developer:** [https://huggingface.co/google](https://huggingface.co/google)
+**Update Date:** 2025-06-27
+**File Size:** 2720 MB
+**Context Length:** 8000 tokens
 **Prompt Format:**
 ```
 ```
 ---
+# SmolLM2 1.7B
+SmolLM2 was trained on 11 trillion tokens and demonstrates significant advances over other small models, particularly in instruction following, knowledge, reasoning, and mathematics.
+**Model Intention:** SmolLM2 is capable of solving a wide range of tasks while being lightweight enough to run on-device
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/smollm2-1.7b-instruct-q4_k_m.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct)
+**Model License:** [License Info](https://choosealicense.com/licenses/apache-2.0/)
+**Model Description:** SmolLM2 was trained on 11 trillion tokens and demonstrates significant advances over other small models, particularly in instruction following, knowledge, reasoning, and mathematics.
+**Developer:** [https://huggingface.co/HuggingFaceTB](https://huggingface.co/HuggingFaceTB)
+**Update Date:** 2024-11-02
+**File Size:** 1060 MB
+**Context Length:** 8192 tokens
 **Prompt Format:**
 ---
+# Phi4 mini 4B
+Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model is intended for broad multilingual commercial and research use. The model provides uses for general purpose AI systems and applications which require: 1). Memory/compute constrained environments; 2). Latency bound scenarios; 3) Strong reasoning (especially math and logic).  The model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.
+**Model Intention:** Phi-4-mini-instruct is a lightweight model focused on high-quality, reasoning dense data. It supports 128K token context length
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Phi-4-mini-instruct-Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Phi-4-mini-instruct-Q4_K_M.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct)
+**Model License:** [License Info](https://choosealicense.com/licenses/mit/)
+**Model Description:** Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model is intended for broad multilingual commercial and research use. The model provides uses for general purpose AI systems and applications which require: 1). Memory/compute constrained environments; 2). Latency bound scenarios; 3) Strong reasoning (especially math and logic).  The model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.
+**Developer:** [https://huggingface.co/microsoft](https://huggingface.co/microsoft)
 **File Size:** 2020 MB
+**Context Length:** 2048 tokens
 **Prompt Format:**
 ```
+{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}
 ```
 **Template Name:** llama3.2
 ---
+# Qwen3 1.7B
+Qwen3 1.7B is one of the small models in the Qwen series, designed for efficiency and speed. It can run seamlessly on edge devices, enabling rapid inference and real-time applications. This compact model is ideal for testing scenarios, prototyping, or deployment in resource-constrained environments.
+**Model Intention:** The 1.7B model in the Qwen3 series is a small model designed for fast predictions and function calls.
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen3-1.7B-Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/Qwen3-1.7B-Q4_K_M.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B)
+**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0.txt)
+**Model Description:** Qwen3 1.7B is one of the small models in the Qwen series, designed for efficiency and speed. It can run seamlessly on edge devices, enabling rapid inference and real-time applications. This compact model is ideal for testing scenarios, prototyping, or deployment in resource-constrained environments.
 **Developer:** [https://huggingface.co/Qwen](https://huggingface.co/Qwen)
+**File Size:** 1110 MB
+**Context Length:** 2048 tokens
 **Prompt Format:**
 ```
 ```
+**Template Name:** qwen
 **Add BOS Token:** Yes
 ---
+# ERNIE-4.5 0.3B
+ERNIE 4.5 is a series of open source models created by Baidu. The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations: 1. Multimodal Heterogeneous MoE Pre-Training; 2. Scaling-Efficient Infrastructure; 3. Modality-Specific Post-Training
+**Model Intention:** ERNIE-4.5-0.3B-Base is a text dense Base model for testing the model's architecture.
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/ERNIE-4.5-0.3B-PT-Q4_0.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/ERNIE-4.5-0.3B-PT-Q4_0.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/baidu/ERNIE-4.5-0.3B-Base-PT](https://huggingface.co/baidu/ERNIE-4.5-0.3B-Base-PT)
+**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0.txt)
+**Model Description:** ERNIE 4.5 is a series of open source models created by Baidu. The advanced capabilities of the ERNIE 4.5 models, particularly the MoE-based A47B and A3B series, are underpinned by several key technical innovations: 1. Multimodal Heterogeneous MoE Pre-Training; 2. Scaling-Efficient Infrastructure; 3. Modality-Specific Post-Training
+**Developer:** [https://huggingface.co/baidu](https://huggingface.co/baidu)
+**File Size:** 233 MB
 **Context Length:** 2048 tokens
 **Prompt Format:**
 ```
 ```
+**Template Name:** qwen
 **Add BOS Token:** Yes
 ---
+# SmolLM3 3B
+SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale. The model is a decoder-only transformer using GQA and NoPE (with 3:1 ratio), it was pretrained on 11.2T tokens with a staged curriculum of web, code, math and reasoning data. Post-training included midtraining on 140B reasoning tokens.
+**Model Intention:** SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages (English, French, Spanish, German, Italian, and Portuguese), advanced reasoning and long context.
+**Model URL:** [https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/SmolLM3-Q4_K_M.gguf?download=true](https://huggingface.co/flyingfishinwater/good_and_small_models/resolve/main/SmolLM3-Q4_K_M.gguf?download=true)
+**Model Info URL:** [https://huggingface.co/HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B)
+**Model License:** [License Info](https://www.apache.org/licenses/LICENSE-2.0.txt)
+**Model Description:** SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale. The model is a decoder-only transformer using GQA and NoPE (with 3:1 ratio), it was pretrained on 11.2T tokens with a staged curriculum of web, code, math and reasoning data. Post-training included midtraining on 140B reasoning tokens.
+**Developer:** [https://huggingface.co/HuggingFaceTB](https://huggingface.co/HuggingFaceTB)
+**File Size:** 1920 MB
 **Context Length:** 2048 tokens
 **Prompt Format:**
 ```
 ```
+**Template Name:** qwen
 **Add BOS Token:** Yes
 **Parse Special Tokens:** Yes
+---