Quantization made by Richard Erkhov.

Github

Discord

Request more models

dolphin-2.9.2-qwen2-7b - GGUF

• Model creator: https://huggingface.co/cognitivecomputations/
• Original model: https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b/

Name	Quant method	Size
dolphin-2.9.2-qwen2-7b.Q2_K.gguf	Q2_K	2.81GB
dolphin-2.9.2-qwen2-7b.IQ3_XS.gguf	IQ3_XS	3.12GB
dolphin-2.9.2-qwen2-7b.IQ3_S.gguf	IQ3_S	3.26GB
dolphin-2.9.2-qwen2-7b.Q3_K_S.gguf	Q3_K_S	3.25GB
dolphin-2.9.2-qwen2-7b.IQ3_M.gguf	IQ3_M	3.33GB
dolphin-2.9.2-qwen2-7b.Q3_K.gguf	Q3_K	3.55GB
dolphin-2.9.2-qwen2-7b.Q3_K_M.gguf	Q3_K_M	3.55GB
dolphin-2.9.2-qwen2-7b.Q3_K_L.gguf	Q3_K_L	3.81GB
dolphin-2.9.2-qwen2-7b.IQ4_XS.gguf	IQ4_XS	3.96GB
dolphin-2.9.2-qwen2-7b.Q4_0.gguf	Q4_0	4.13GB
dolphin-2.9.2-qwen2-7b.IQ4_NL.gguf	IQ4_NL	4.16GB
dolphin-2.9.2-qwen2-7b.Q4_K_S.gguf	Q4_K_S	4.15GB
dolphin-2.9.2-qwen2-7b.Q4_K.gguf	Q4_K	4.36GB
dolphin-2.9.2-qwen2-7b.Q4_K_M.gguf	Q4_K_M	4.36GB
dolphin-2.9.2-qwen2-7b.Q4_1.gguf	Q4_1	4.54GB
dolphin-2.9.2-qwen2-7b.Q5_0.gguf	Q5_0	4.95GB
dolphin-2.9.2-qwen2-7b.Q5_K_S.gguf	Q5_K_S	4.95GB
dolphin-2.9.2-qwen2-7b.Q5_K.gguf	Q5_K	5.07GB
dolphin-2.9.2-qwen2-7b.Q5_K_M.gguf	Q5_K_M	5.07GB
dolphin-2.9.2-qwen2-7b.Q5_1.gguf	Q5_1	5.36GB
dolphin-2.9.2-qwen2-7b.Q6_K.gguf	Q6_K	5.82GB
dolphin-2.9.2-qwen2-7b.Q8_0.gguf	Q8_0	7.54GB

Original model description:

license: apache-2.0 base_model: Qwen/Qwen2-7B tags:

• generated_from_trainer
• axolotl datasets:
• cognitivecomputations/Dolphin-2.9
• teknium/OpenHermes-2.5
• m-a-p/CodeFeedback-Filtered-Instruction
• cognitivecomputations/dolphin-coder
• cognitivecomputations/samantha-data
• microsoft/orca-math-word-problems-200k
• Locutusque/function-calling-chatml
• internlm/Agent-FLAN

---

Dolphin 2.9.2 Qwen2 7B 🐬

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsors of Dolphin 2.9.2:

• Crusoe Cloud - provided excellent on-demand 8xH100 node

This model is based on Qwen2-7b, and is governed by tongyi-qianwen license

The base model has 128k context, and the full-weight fine-tuning was with 16k sequence length.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.

Dolphin is uncensored. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Dolphin is licensed according to Qwen's tongyi-qianwen license. We grant permission for any use, including commercial, that falls within accordance with said license. Dolphin was trained on data generated from GPT4, among other models.

Evals