Quantization made by Richard Erkhov.
blossom-v5-9b - GGUF
- Model creator: https://huggingface.co/Azure99/
- Original model: https://huggingface.co/Azure99/blossom-v5-9b/
Name | Quant method | Size |
---|---|---|
blossom-v5-9b.Q2_K.gguf | Q2_K | 3.12GB |
blossom-v5-9b.IQ3_XS.gguf | IQ3_XS | 3.46GB |
blossom-v5-9b.IQ3_S.gguf | IQ3_S | 3.64GB |
blossom-v5-9b.Q3_K_S.gguf | Q3_K_S | 3.63GB |
blossom-v5-9b.IQ3_M.gguf | IQ3_M | 3.78GB |
blossom-v5-9b.Q3_K.gguf | Q3_K | 4.03GB |
blossom-v5-9b.Q3_K_M.gguf | Q3_K_M | 4.03GB |
blossom-v5-9b.Q3_K_L.gguf | Q3_K_L | 4.37GB |
blossom-v5-9b.IQ4_XS.gguf | IQ4_XS | 4.5GB |
blossom-v5-9b.Q4_0.gguf | Q4_0 | 4.69GB |
blossom-v5-9b.IQ4_NL.gguf | IQ4_NL | 4.73GB |
blossom-v5-9b.Q4_K_S.gguf | Q4_K_S | 4.72GB |
blossom-v5-9b.Q4_K.gguf | Q4_K | 4.96GB |
blossom-v5-9b.Q4_K_M.gguf | Q4_K_M | 4.96GB |
blossom-v5-9b.Q4_1.gguf | Q4_1 | 5.19GB |
blossom-v5-9b.Q5_0.gguf | Q5_0 | 5.69GB |
blossom-v5-9b.Q5_K_S.gguf | Q5_K_S | 5.69GB |
blossom-v5-9b.Q5_K.gguf | Q5_K | 5.83GB |
blossom-v5-9b.Q5_K_M.gguf | Q5_K_M | 5.83GB |
blossom-v5-9b.Q5_1.gguf | Q5_1 | 6.19GB |
blossom-v5-9b.Q6_K.gguf | Q6_K | 6.75GB |
blossom-v5-9b.Q8_0.gguf | Q8_0 | 8.74GB |
Original model description:
license: apache-2.0 datasets: - Azure99/blossom-chat-v3 - Azure99/blossom-math-v4 - Azure99/blossom-wizard-v3 - Azure99/blossom-orca-v3 language: - zh - en
BLOSSOM-v5-9b
What's new?
The Blossom V5 series models is fully trained using high-quality data distilled from gpt-4-0125-preview, resulting in significant improvements.
Introduction
Blossom is a conversational large language model, fine-tuned on the Blossom Orca/Wizard/Chat/Math mixed dataset based on the Yi-9B pre-trained model. Blossom possesses robust general capabilities and context comprehension. Additionally, the high-quality Chinese and English datasets used for training have been made open source.
Training was conducted in two stages. The first stage used 40K Wizard, 40K Orca, 10K Math single-turn instruction datasets, training for 1 epoch; the second stage used 10K Blossom chat multi-turn dialogue dataset, and 10% randomly sampled data from the first stage, training for 3 epochs.
Inference
Inference is performed in the form of dialogue continuation.
Single-turn dialogue
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|:
Multi-turn dialogue
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: hello
|Bot|: Hello! How can I assist you today?<|endoftext|>
|Human|: Generate a random number using python
|Bot|:
Note: At the end of the Bot's output in the historical conversation, append a <|endoftext|>
.
- Downloads last month
- 233