LLM EXPLORER 59,278 MODELS INDEXED

Bellman 7B Mistral Instruct V0.2 by neph1

By neph1 · 361 downloads
HF Repo ↗ Copy URL

Bellman 7B Mistral Instruct V0.2 is an open-source language model by neph1. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.1.

  Conversational Dataset:neph1/bellman-7b-finet... Dataset:neph1/truthy-dpo-v0.1-...   Endpoints compatible   Gguf   Instruct   Mistral   Region:us   Safetensors   Sharded   Sv   Tensorflow
Model Card on HF 🤗: https://huggingface.co/neph1/bellman-7b-mistral-instruct-v0.2 

Bellman 7B Mistral Instruct V0.2 Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Language Assistance
Applications:
Swedish language enhancement, Q&A applications
Primary Use Cases:
Swedish language instruction, Q&A model
Limitations:
May provide inaccurate information due to creative intent
Considerations:
Take outputs with a grain of salt due to creative and sometimes inaccurate responses.
Additional Notes 
Named after Swedish bard Carl Mikael Bellman, emphasizing creative and cultural dimensions of communication.
Supported Languages 
sv (Intermediate)
Training Details 
Data Sources:
neph1/bellman-7b-finetune, neph1/truthy-dpo-v0.1-swe
Data Volume:
14,000 rows of Q&A, Python examples, and general 'instruct' type questions
Methodology:
Qlora trained for ~2 epochs with a focus on improving Swedish topic knowledge and language quality
Context Length:
4096
Training Time:
ca 2 epochs
Model Architecture:
Light DPO pass to align the model
Input Output 
Input Format:
[INST]...[/INST]
Accepted Modalities:
text
Output Format:
Text in Swedish
Performance Tips:
Use correct prompt format and Swedish phrasing for improved results.
Release Notes 
Version:
latest
Date:
2023-04-13
Notes:
Dataset: 14002 rows. Increased diversity of instructional content with alignments to reduce misinformation tendencies.
LLM NameBellman 7B Mistral Instruct V0.2
Repository 🤗https://huggingface.co/neph1/bellman-7b-mistral-instruct-v0.2 
Model Size7b
Required VRAM14.4 GB
Updated2026-07-18
Maintainerneph1
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagessv
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Bellman 7B Mistral Instruct V0.2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB22020
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB100
...1 Summarize 64K LoRANET Merged128K / 14.4 GB130
Mistral 7B Instruct V0.232K / 14.4 GB11153373184
Mistral 7B Instruct V0.132K / 14.4 GB2536291846
Mistral 7B Instruct V0.232K / 14.4 GB13380
Lexi Coder V5.132K / 14.5 GB1970
Note: green Score (e.g. "73.2") means that the model is better than neph1/bellman-7b-mistral-instruct-v0.2.