mlabonne commited on
Commit
005bf33
·
verified ·
1 Parent(s): 0c0603c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -208,7 +208,7 @@ You can directly run and test the model with this [Colab notebook](https://colab
208
  You need to install [`vLLM`](https://github.com/vllm-project/vllm) v0.10.2 or a more recent version as follows:
209
 
210
  ```bash
211
- uv pip install vllm --extra-index-url https://wheels.vllm.ai/0.10.2/ --torch-backend=auto
212
  ```
213
 
214
  Here is an example of how to use it for inference:
@@ -223,7 +223,7 @@ prompts = [
223
  ]
224
  sampling_params = SamplingParams(temperature=0.3, min_p=0.15, repetition_penalty=1.05)
225
 
226
- llm = LLM(model="LiquidAI/LFM2-350M")
227
 
228
  outputs = llm.generate(prompts, sampling_params)
229
 
@@ -257,10 +257,10 @@ LFM2 outperforms similar-sized models across different evaluation categories. We
257
  | Model | MMLU | GPQA | IFEval | IFBench | GSM8K | MGSM | MMMLU |
258
  | ---------------------- | ----- | ----- | ------ | ------- | ----- | ----- | ----- |
259
  | LFM2-2.6B | 64.42 | 26.57 | 79.56 | 22.19 | 82.41 | 74.32 | 55.39 |
260
- | Qwen3-4B-Instruct-2507 | 72.25 | 34.85 | 85.62 | 30.28 | 68.46 | 81.76 | 60.67 |
261
  | SmolLM3-3B | 59.84 | 26.31 | 72.44 | 17.93 | 81.12 | 68.72 | 50.02 |
262
  | gemma-3-4b-it | 58.35 | 29.51 | 76.85 | 23.53 | 89.92 | 87.28 | 50.14 |
263
- | Llama-3.2-3B-Instruct | 60.35 | 30.6 | 71.43 | 20.78 | 75.21 | 61.68 | 47.92 |
264
 
265
  ## 📬 Contact
266
 
 
208
  You need to install [`vLLM`](https://github.com/vllm-project/vllm) v0.10.2 or a more recent version as follows:
209
 
210
  ```bash
211
+ uv pip install vllm==0.10.2 --extra-index-url https://wheels.vllm.ai/0.10.2/ --torch-backend=auto
212
  ```
213
 
214
  Here is an example of how to use it for inference:
 
223
  ]
224
  sampling_params = SamplingParams(temperature=0.3, min_p=0.15, repetition_penalty=1.05)
225
 
226
+ llm = LLM(model="LiquidAI/LFM2-2.6B")
227
 
228
  outputs = llm.generate(prompts, sampling_params)
229
 
 
257
  | Model | MMLU | GPQA | IFEval | IFBench | GSM8K | MGSM | MMMLU |
258
  | ---------------------- | ----- | ----- | ------ | ------- | ----- | ----- | ----- |
259
  | LFM2-2.6B | 64.42 | 26.57 | 79.56 | 22.19 | 82.41 | 74.32 | 55.39 |
260
+ | Llama-3.2-3B-Instruct | 60.35 | 30.6 | 71.43 | 20.78 | 75.21 | 61.68 | 47.92 |
261
  | SmolLM3-3B | 59.84 | 26.31 | 72.44 | 17.93 | 81.12 | 68.72 | 50.02 |
262
  | gemma-3-4b-it | 58.35 | 29.51 | 76.85 | 23.53 | 89.92 | 87.28 | 50.14 |
263
+ | Qwen3-4B-Instruct-2507 | 72.25 | 34.85 | 85.62 | 30.28 | 68.46 | 81.76 | 60.67 |
264
 
265
  ## 📬 Contact
266