Eval
Before finetuning (unsloth/Qwen3-4B-unsloth-bnb-4bit)
| Model | Dataset | Metric | Subset | Num | Score | Cat.0 |
|---|---|---|---|---|---|---|
| qwen | gpqa | AveragePass@1 | gpqa_extended | 50 | 0.24 | default |
| qwen | gpqa | AveragePass@1 | gpqa_main | 50 | 0.26 | default |
| qwen | gpqa | AveragePass@1 | gpqa_diamond | 50 | 0.22 | default |
| qwen | gpqa | AveragePass@1 | OVERALL | 150 | 0.24 | - |
| qwen | gsm8k | AverageAccuracy | main | 50 | 0.50 | default |
| qwen | tool_bench | Act.EM | in_domain | 42 | 0.1667 | default |
| qwen | tool_bench | Act.EM | out_of_domain | 48 | 0.1667 | default |
| qwen | tool_bench | Act.EM | OVERALL | 90 | 0.1667 | - |
After finetuning (This model)
| Model | Dataset | Metric | Subset | Num | Score | Cat.0 |
|---|---|---|---|---|---|---|
| model | gpqa | AveragePass@1 | gpqa_extended | 50 | 0.26 | default |
| model | gpqa | AveragePass@1 | gpqa_main | 50 | 0.36 | default |
| model | gpqa | AveragePass@1 | gpqa_diamond | 50 | 0.38 | default |
| model | gpqa | AveragePass@1 | OVERALL | 150 | 0.3333 | - |
| model | gsm8k | AverageAccuracy | main | 50 | 0.68 | default |
| model | tool_bench | Act.EM | in_domain | 41 | 0.3171 | default |
| model | tool_bench | Act.EM | out_of_domain | 47 | 0.3191 | default |
| model | tool_bench | Act.EM | OVERALL | 88 | 0.3182 | - |
Qwen/Qwen3-4B model
| Model | Dataset | Metric | Subset | Num | Score | Cat.0 |
|---|---|---|---|---|---|---|
| model | gpqa | AveragePass@1 | gpqa_extended | 50 | 0.32 | default |
| model | gpqa | AveragePass@1 | gpqa_main | 50 | 0.22 | default |
| model | gpqa | AveragePass@1 | gpqa_diamond | 50 | 0.18 | default |
| model | gpqa | AveragePass@1 | OVERALL | 150 | 0.24 | - |
| model | gsm8k | AverageAccuracy | main | 50 | 0.48 | default |
| model | tool_bench | Act.EM | in_domain | 43 | 0.1628 | default |
| model | tool_bench | Act.EM | out_of_domain | 47 | 0.1702 | default |
| model | tool_bench | Act.EM | OVERALL | 90 | 0.1667 | - |
Use this model
with llama-cli
llama-cli -m Qwen3-4B-toolcall.Q4_K_M.gguf
with ollama
- edit a makefile named(Qwen3-4B-toolcall.Q4_K_M.txt) like:
FROM ./Qwen3-4B-toolcall.Q4_K_M TEMPLATE """<|im_start|>system You are a helpful assistant<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant """- then create a model using ollama
ollama create Qwen3-4B-toolcall.Q4_K_M -f Qwen3-4B-toolcall.Q4_K_M.txt- then run it
ollama run Qwen3-4B-toolcall.Q4_K_M