Model Card for traclm-v2-7b-instruct-GGUF
This repo contains several GGUF quantizations of TRAC-MTRY/traclm-v2-7b-instruct for utilization of the model on low-resource hardware.
Available quantizations are listed here:
Name | Quant method | Bits | Size | Use case |
---|---|---|---|---|
TRAC-MTRY/traclm-v2-7b-instruct-2q_k | Q2_K | 2 | 2.83 GB | smallest, significant quality loss - not recommended for most purposes |
TRAC-MTRY/traclm-v2-7b-instruct-3q_k_m | Q3_K_M | 3 | 3.3 GB | very small, high quality loss |
TRAC-MTRY/traclm-v2-7b-instruct-4q_k_m | Q4_K_M | 4 | 4.08 GB | medium, balanced quality - recommended |
TRAC-MTRY/traclm-v2-7b-instruct-5q_k_m | Q5_K_M | 5 | 4.78 GB | large, very low quality loss - recommended |
TRAC-MTRY/traclm-v2-7b-instruct-6q_k_m | Q6_K | 6 | 5.53 GB | very large, extremely low quality loss |
Note: an fp16 unquantized version in GGUF format is also provided, see repo files.
Read more about GGUF quantization here.
Read more about the unquantized model here.
Prompt Format
This model was fine-tuned with the alpaca prompt format. It is highly recommended that you use the same format for any interactions with the model. Failure to do so will degrade performance significantly.
Standard Alpaca Format:
### System:\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n\n\n### Instruction:\n{prompt}\n\n### Response:\n "
Input Field Variant:
### System:\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n\n\n\n### Instruction:\n{prompt}\n\n###Input:\n{input}\n\n### Response:\n "
- Downloads last month
- 0