Hemlock2 Coder 7B is an open-source language model by hemlang. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, Instruction-Based, Code Generating.
Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-... Codegen Conversational Dataset:hemlang/hemlock2-dpo Endpoints compatible Grimoire Instruct Merlina Orpo Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/hemlang/Hemlock2-Coder-7B
Hemlock2 Coder 7B Parameters and Internals
| LLM Name | Hemlock2 Coder 7B |
| Repository 🤗 | https://huggingface.co/hemlang/Hemlock2-Coder-7B |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2026-04-15 |
| Maintainer | hemlang |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 5.2.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Errors | replace |
Best Alternatives to Hemlock2 Coder 7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Rebase | 986K / 15.2 GB | 73 | 2 |
| Qwen2.5 7B Rebase | 986K / 15.2 GB | 7 | 2 |
| StockQwen 2.5 7B | 128K / 15.2 GB | 25 | 6 |
| DareQwen 2.5 7B | 128K / 15.2 GB | 0 | 1 |
| Tessa T1 7B | 117K / 15.2 GB | 12 | 10 |
| UIGEN T1.5 7B | 117K / 15.2 GB | 5 | 6 |
| Qwen2.5 Coder 7B Instruct | 32K / 15.2 GB | 2110918 | 684 |
| Qwen2.5 Coder 7B Instruct MLX | 32K / 15.2 GB | 799 | 2 |
| Qwen2.5 7B MS Destroyer | 32K / 15.2 GB | 7 | 1 |
| Viper Coder HybridMini V1.3 | 32K / 15.2 GB | 30 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than hemlang/Hemlock2-Coder-7B .
Rank the Hemlock2 Coder 7B 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! 🌟
What open-source LLMs or SLMs are you in search of? 52861 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a