LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Speechless Codellama 34B V2.0 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Speechless Codellama 34B V2.0 AWQ   URL Share it on

  1   

Speechless Codellama 34B V2.0 AWQ is an open-source language model by TheBloke. Features: 34b LLM, VRAM: 18.3GB, Context: 16K, License: llama2, Quantized, Instruction-Based, Code Generating, LLM Explorer Score: 0.11.

  Arxiv:2308.12950   4-bit   Awq Base model:quantized:uukuguy/s... Base model:uukuguy/speechless-...   Code   Codegen Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-2....   Dataset:open-orca/openorca Dataset:wizardlm/wizardlm evol...   En   Instruct   Llama   Llama2   Model-index   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ 

Speechless Codellama 34B V2.0 AWQ Benchmarks

LLME Score: 0.10547
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Speechless Codellama 34B V2.0 AWQ (TheBloke/speechless-codellama-34b-v2.0-AWQ)
🌟 Advertise your project 🚀

Speechless Codellama 34B V2.0 AWQ Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial and research
Applications:
code synthesis, code understanding
Limitations:
Testing conducted has been in English, potential outputs cannot be predicted in advance, may produce inaccurate or objectionable responses.
Considerations:
Perform safety testing and tuning tailored to specific applications of the model.
Additional Notes 
Utilizes AWQ, a low-bit weight quantization method to reduce hardware requirements.
Training Details 
Data Sources:
jondurbin/airoboros-2.2, Open-Orca/OpenOrca, garage-bAInd/Open-Platypus, WizardLM/WizardLM_evol_instruct_V2_196k
Context Length:
16384
Training Time:
1 day, 14:42:57.87
Hardware Used:
A100-80G x 2
Safety Evaluation 
Ethical Considerations:
Use in any manner that violates applicable laws or regulations (including trade compliance laws) is prohibited. Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Utilizes AWQ for efficient 4-bit quantization, allowing smaller GPUs.
LLM NameSpeechless Codellama 34B V2.0 AWQ
Repository 🤗https://huggingface.co/TheBloke/speechless-codellama-34b-v2.0-AWQ 
Model NameSpeechless Codellama 34B v2.0
Model CreatorJiangwen Su
Base Model(s)  uukuguy/speechless-codellama-34b-v2.0   uukuguy/speechless-codellama-34b-v2.0
Model Size34b
Required VRAM18.3 GB
Updated2026-01-19
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-2   8.4 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Speechless Codellama 34B V2.0 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Instruct AWQ16K / 18.3 GB1761
CodeLlama 34B Instruct Fp1616K / 67.5 GB28196
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB682
...0 Uncensored CodeLlama 34B AWQ16K / 18.3 GB272
...gpt 32K Codellama 34B Instruct32K / 67.5 GB842
CodeLlama 34B Instruct Hf16K / 67.5 GB13339304
Speechless Codellama 34B V2.016K / 67.5 GB54917
Speechless Codellama 34B V1.916K / 67.5 GB17520
CodeLlama 34B Instruct Hf16K / 67.5 GB25517
XAgentLLaMa 34B Preview16K / 157.3 GB123
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/speechless-codellama-34b-v2.0-AWQ.

Rank the Speechless Codellama 34B V2.0 AWQ Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51638 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20241124
  Support LLM Explorer