LLM EXPLORER 61,755 MODELS INDEXED

Dolphin 2.6 Mixtral 8x7b by cognitivecomputations

By cognitivecomputations · 11285 downloads
HF Repo ↗ Copy URL

Dolphin 2.6 Mixtral 8x7b is an open-source language model by cognitivecomputations. Features: LLM, VRAM: 93.6GB, Context: 32K, License: apache-2.0, MoE, Instruction-Based, LLM Explorer Score: 0.14.

  Autotrain compatible   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/dolphin-code... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:jondurbin/airoboros-2....   Dataset:ldjnr/capybara   Dataset:teknium/openhermes   En   Endpoints compatible   Instruct   Mixtral   Moe   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.6-mixtral-8x7b 

Dolphin 2.6 Mixtral 8x7b Parameters and Internals

Use Cases 
Areas:
General Chat, Structured Output, Agent Cases (Autogen, Memgpt, Functions), Role-playing
Applications:
Coding Assistance, LeetCode Problems
Primary Use Cases:
Coding, Chatbot
Limitations:
May not be ethically aligned without an additional layer
Considerations:
Implement alignment layer before exposing as service.
Additional Notes 
Model is highly compliant to any requests, even unethical ones. It is recommended to implement your own alignment layer.
Supported Languages 
en (Fully supported)
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/dolphin-coder, teknium/openhermes, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, LDJnr/Capybara
Methodology:
qLoRA and Axolotl
Context Length:
16000
Training Time:
3 days (1.5 epochs on 4x A100s)
Hardware Used:
4x A100s
Responsible Ai Considerations 
Fairness:
Dataset was filtered to remove alignment and bias.
Accountability:
User is responsible for content created using the model.
Mitigation Strategies:
Recommended to implement own alignment layer before exposing as a service.
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Implement own alignment layer for ethical and safe deployment.
LLM NameDolphin 2.6 Mixtral 8x7b
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.6-mixtral-8x7b 
Required VRAM93.6 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typemixtral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-19   5.0 GB: 2-of-19   5.0 GB: 3-of-19   4.9 GB: 4-of-19   5.0 GB: 5-of-19   5.0 GB: 6-of-19   4.9 GB: 7-of-19   5.0 GB: 8-of-19   5.0 GB: 9-of-19   4.9 GB: 10-of-19   5.0 GB: 11-of-19   5.0 GB: 12-of-19   5.0 GB: 13-of-19   4.9 GB: 14-of-19   5.0 GB: 15-of-19   5.0 GB: 16-of-19   4.9 GB: 17-of-19   5.0 GB: 18-of-19   4.2 GB: 19-of-19
Supported Languagesen
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Dolphin 2.6 Mixtral 8x7b

Model
Likes
Downloads
VRAM
Dolphin 2.6 Mixtral 8x7b GGUF49152715 GB
Dolphin 2.6 Mixtral 8x7b AWQ123224 GB
Dolphin 2.6 Mixtral 8x7b GPTQ61223 GB

Best Alternatives to Dolphin 2.6 Mixtral 8x7b

Best Alternatives
Context / RAM
Downloads
Likes
...ixtral 8x22B Instruct V0.1 FP864K / 140.9 GB980
Dolphin 2.6 Mixtral 8x7b32K / 93.6 GB7806217
...eqlen 4096 Bs 4 Optimum 0 0 2332K /  GB80
...eqlen 4096 Bs 4 Optimum 0 0 2332K /  GB91
Dolphin 2.7 Mixtral 8x7b32K / 93.6 GB2178170
Empower Functions Medium32K / 93.6 GB171
Mixtral 8x7B Instruct V0.132K /  GB50
...ral 8x7b Instruct V0.1 Int4 Ov32K / 0 GB164
Dolphin 2.7 Mixtral 8x7b32K / 93.6 GB228169
...ct V0.1 Agent Function Calling32K / 44.3 GB42
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.6-mixtral-8x7b.