Update README.md

.gitattributes

@@ -40,9 +40,3 @@ assets/tuto_open_hands/agent_working.png filter=lfs diff=lfs merge=lfs -text
 assets/tuto_open_hands/build_app.png filter=lfs diff=lfs merge=lfs -text
 assets/tuto_open_hands/agent_prompting.png filter=lfs diff=lfs merge=lfs -text
 assets/tuto_open_hands/app_ui.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_1.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_2.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_3.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_res_1.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_res_2.png filter=lfs diff=lfs merge=lfs -text
-assets/images_example/example_mistral_common_res_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -35,7 +35,7 @@ extra_gated_description: >-
 pipeline_tag: text2text-generation
 ---
 
-# Devstral-Small-2505
+# Devstrall-Small-2505
 
 Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results). 
 
@@ -107,7 +107,6 @@ The model can also be deployed with the following libraries:
 - [`mistral-inference`](https://github.com/mistralai/mistral-inference): See [here](#mistral-inference)
 - [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
 - [`LMStudio`](https://lmstudio.ai/): See [here](#lmstudio)
-- [`llama.cpp`](https://github.com/ggml-org/llama.cpp): See [here](#llama.cpp)
 - [`ollama`](https://github.com/ollama/ollama): See [here](#ollama)
 
 
@@ -322,6 +321,7 @@ from mistral_common.protocol.instruct.messages import (
 )
 from mistral_common.protocol.instruct.request import ChatCompletionRequest
 from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
 from huggingface_hub import hf_hub_download
 from transformers import AutoModelForCausalLM
 
@@ -372,7 +372,7 @@ You can serve the model locally with [LMStudio](https://lmstudio.ai/).
 * Download [LM Studio](https://lmstudio.ai/) and install it
 * Install `lms cli ~/.lmstudio/bin/lms bootstrap`
 * In a bash terminal, run `lms import devstralQ4_K_M.gguf` in the directory where you've downloaded the model checkpoint (e.g. `mistralai/Devstral-Small-2505_gguf`)
-* Open the LMStudio application, click the terminal icon to get into the developer tab. Click select a model to load and select Devstral Q4 K M. Toggle the status button to start the model, in setting toggle Serve on Local Network to be on.
+* Open the LMStudio application, click the terminal icon to get into the developer tab. Click select a model to load and select Devstral Q4 K M. Toggle the status button to start the model, in setting oggle Serve on Local Network to be on.
 * On the right tab, you will see an API identifier which should be devstralq4_k_m and an api address under API Usage. Keep note of this address, we will use it in the next step.
 
 Launch Openhands
@@ -394,23 +394,6 @@ docker run -it --rm --pull=always \
 Click “see advanced setting” on the second line. 
 In the new tab, toggle advanced to on. Set the custom model to be mistral/devstralq4_k_m and Base URL the api address we get from the last step in LM Studio. Set API Key to dummy. Click save changes.
 
-### llama.cpp
-
-Download the weights from huggingface:
-
-```
-pip install -U "huggingface_hub[cli]"
-huggingface-cli download \
-"mistralai/Devstral-Small-2505_gguf" \
---include "devstralQ4_K_M.gguf" \
---local-dir "mistralai/Devstral-Small-2505_gguf/"
-```
-
-Then run Devstral using the llama.cpp CLI.
-
-```bash
-./llama-cli -m Devstral-Small-2505_gguf/devstralQ4_K_M.gguf -cnv
-```
 
 ### Ollama
 
@@ -418,34 +401,4 @@ You can run Devstral using the [Ollama](https://ollama.ai/) CLI.
 
 ```bash
 ollama run devstral
-```
-
-### Example: Understanding Test Coverage of Mistral Common
-
-We can start the OpenHands scaffold and link it to a repo to analyze test coverage and identify badly covered files.
-Here we start with our public `mistral-common` repo.
-
-
-After the repo is mounted in the workspace, we give the following instruction
-```
-Check the test coverage of the repo and then create a visualization of test coverage. Try plotting a few different types of graphs and save them to a png.
-```
-The agent will first browse the code base to check test configuration and structure.
-
-![Repo Exploration](assets/images_example/example_mistral_common_1.png)
-
-Then it sets up the testing dependencies and launches the coverage test:
-
-![Repo Exploration](assets/images_example/example_mistral_common_2.png)
-
-Finally, the agent writes necessary code to visualize the coverage.
-![Repo Exploration](assets/images_example/example_mistral_common_3.png)
-
-At the end of the run, the following plots are produced:
-![Repo Exploration](assets/images_example/example_mistral_common_res_1.png)
-![Repo Exploration](assets/images_example/example_mistral_common_res_2.png)
-![Repo Exploration](assets/images_example/example_mistral_common_res_3.png)
-
-
-
-
+```