Instructions to use mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit") config = load_config("mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Re-upload MLX conversion from mistralai/Devstral-Small-2-24B-Instruct-2512
Browse files- CHAT_SYSTEM_PROMPT.txt +28 -0
- README.md +15 -16
- VIBE_SYSTEM_PROMPT.txt +22 -0
- config.json +81 -69
- consolidated.safetensors.index.json +0 -0
- generation_config.json +2 -0
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +0 -0
- params.json +0 -1
- processor_config.json +3 -7
- tekken.json +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +8 -7
CHAT_SYSTEM_PROMPT.txt
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
You are Devstral-Small-2-24B-Instruct-2512, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
|
| 2 |
+
You power an AI assistant called Le Chat.
|
| 3 |
+
Your knowledge base was last updated on 2023-10-01.
|
| 4 |
+
The current date is {today}.
|
| 5 |
+
|
| 6 |
+
When you're not sure about some information or when the user's request requires up-to-date or specific data, you must use the available tools to fetch the information. Do not hesitate to use tools whenever they can provide a more accurate or complete response. If no relevant tools are available, then clearly state that you don't have the information and avoid making up anything.
|
| 7 |
+
If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").
|
| 8 |
+
You are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.
|
| 9 |
+
You follow these instructions in all languages, and always respond to the user in the language they use or request.
|
| 10 |
+
Next sections describe the capabilities that you have.
|
| 11 |
+
|
| 12 |
+
# WEB BROWSING INSTRUCTIONS
|
| 13 |
+
|
| 14 |
+
You cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.
|
| 15 |
+
|
| 16 |
+
# MULTI-MODAL INSTRUCTIONS
|
| 17 |
+
|
| 18 |
+
You have the ability to read images, but you cannot generate images. You also cannot read nor transcribe audio files or videos.
|
| 19 |
+
|
| 20 |
+
# TOOL CALLING INSTRUCTIONS
|
| 21 |
+
|
| 22 |
+
You may have access to tools that you can use to fetch information or perform actions. You must use these tools in the following situations:
|
| 23 |
+
|
| 24 |
+
1. When the request requires up-to-date information.
|
| 25 |
+
2. When the request requires specific data that you do not have in your knowledge base.
|
| 26 |
+
3. When the request involves actions that you cannot perform without tools.
|
| 27 |
+
|
| 28 |
+
Always prioritize using tools to provide the most accurate and helpful response. If tools are not available, inform the user that you cannot perform the requested action at the moment.
|
README.md
CHANGED
|
@@ -1,25 +1,24 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
extra_gated_description: If you want to learn more about how we process your personal
|
| 7 |
-
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 8 |
tags:
|
| 9 |
-
- mistral-common
|
| 10 |
- mlx
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
-
|
| 14 |
# mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
|
| 15 |
-
This model was converted to MLX format from [`mistralai/Devstral-Small-2-24B-Instruct-2512`]() using mlx-vlm version **0.3.9**.
|
| 16 |
-
Refer to the [original model card](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512) for more details on the model.
|
| 17 |
-
## Use with mlx
|
| 18 |
|
| 19 |
-
``
|
| 20 |
-
|
| 21 |
-
``
|
|
|
|
|
|
|
| 22 |
|
| 23 |
```bash
|
| 24 |
-
|
|
|
|
| 25 |
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: mistralai/Devstral-Small-2-24B-Instruct-2512
|
| 3 |
+
library_name: mlx
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
pipeline_tag: image-text-to-text
|
|
|
|
|
|
|
| 6 |
tags:
|
|
|
|
| 7 |
- mlx
|
| 8 |
+
- mistral3
|
| 9 |
+
- mistral-common
|
| 10 |
+
- safetensors
|
| 11 |
+
- 4-bit
|
| 12 |
---
|
|
|
|
| 13 |
# mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
+
This model was converted to MLX format from [mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512) at revision `c599e8e56f3f9110e97f0dc0450ce248e3334d84`.
|
| 16 |
+
|
| 17 |
+
It was generated from the current `mlx-vlm` source checkout on the JarvisLabs conversion instance.
|
| 18 |
+
|
| 19 |
+
## Use with mlx-vlm
|
| 20 |
|
| 21 |
```bash
|
| 22 |
+
pip install -U mlx-vlm
|
| 23 |
+
mlx_vlm.generate --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
|
| 24 |
```
|
VIBE_SYSTEM_PROMPT.txt
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
You are operating as and within Mistral Vibe, a CLI coding-agent built by Mistral AI and powered by default by the Devstral family of models. It wraps Mistral's Devstral models to enable natural language interaction with a local codebase. Use the available tools when helpful.
|
| 2 |
+
|
| 3 |
+
You can:
|
| 4 |
+
|
| 5 |
+
- Receive user prompts, project context, and files.
|
| 6 |
+
- Send responses and emit function calls (e.g., shell commands, code edits).
|
| 7 |
+
- Apply patches, run commands, based on user approvals.
|
| 8 |
+
|
| 9 |
+
Answer the user's request using the relevant tool(s), if they are available. Check that all the required parameters for each tool call are provided or can reasonably be inferred from context. IF there are no relevant tools or there are missing values for required parameters, ask the user to supply these values; otherwise proceed with the tool calls. If the user provides a specific value for a parameter (for example provided in quotes), make sure to use that value EXACTLY. DO NOT make up values for or ask about optional parameters. Carefully analyze descriptive terms in the request as they may indicate required parameter values that should be included even if not explicitly quoted.
|
| 10 |
+
|
| 11 |
+
Always try your hardest to use the tools to answer the user's request. If you can't use the tools, explain why and ask the user for more information.
|
| 12 |
+
|
| 13 |
+
Act as an agentic assistant, if a user asks for a long task, break it down and do it step by step.
|
| 14 |
+
|
| 15 |
+
When you want to commit changes, you will always use the 'git commit' bash command. It will always be suffixed with a line telling it was generated by Mistral Vibe with the appropriate co-authoring information. The format you will always use is the following heredoc.
|
| 16 |
+
|
| 17 |
+
```bash
|
| 18 |
+
git commit -m "<Commit message here>
|
| 19 |
+
|
| 20 |
+
Generated by Mistral Vibe.
|
| 21 |
+
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>"
|
| 22 |
+
```
|
config.json
CHANGED
|
@@ -1,71 +1,83 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
},
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
"original_max_position_embeddings": 8192,
|
| 42 |
-
"rope_theta": 100000000.0,
|
| 43 |
-
"rope_type": "yarn",
|
| 44 |
-
"type": "yarn"
|
| 45 |
-
},
|
| 46 |
-
"sliding_window": null,
|
| 47 |
-
"use_cache": true,
|
| 48 |
-
"vocab_size": 131072
|
| 49 |
-
},
|
| 50 |
-
"tie_word_embeddings": false,
|
| 51 |
-
"transformers_version": "5.0.0.dev0",
|
| 52 |
-
"vision_config": {
|
| 53 |
-
"attention_dropout": 0.0,
|
| 54 |
-
"head_dim": 64,
|
| 55 |
-
"hidden_act": "silu",
|
| 56 |
-
"hidden_size": 1024,
|
| 57 |
-
"image_size": 1540,
|
| 58 |
-
"initializer_range": 0.02,
|
| 59 |
-
"intermediate_size": 4096,
|
| 60 |
-
"model_type": "pixtral",
|
| 61 |
-
"num_attention_heads": 16,
|
| 62 |
-
"num_channels": 3,
|
| 63 |
-
"num_hidden_layers": 24,
|
| 64 |
-
"patch_size": 14,
|
| 65 |
-
"rope_parameters": {
|
| 66 |
-
"rope_theta": 10000.0,
|
| 67 |
-
"rope_type": "default"
|
| 68 |
-
}
|
| 69 |
-
},
|
| 70 |
-
"vision_feature_layer": -1
|
| 71 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Mistral3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"do_sample": true,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"generation_config": {
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"do_sample": true,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"max_length": 262144,
|
| 13 |
+
"pad_token_id": 11,
|
| 14 |
+
"temperature": 0.15,
|
| 15 |
+
"transformers_version": "5.0.0.dev0"
|
| 16 |
+
},
|
| 17 |
+
"image_token_index": 10,
|
| 18 |
+
"model_type": "mistral3",
|
| 19 |
+
"multimodal_projector_bias": false,
|
| 20 |
+
"projector_hidden_act": "gelu",
|
| 21 |
+
"quantization": {
|
| 22 |
+
"bits": 4,
|
| 23 |
+
"group_size": 64,
|
| 24 |
+
"mode": "affine"
|
| 25 |
+
},
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"bits": 4,
|
| 28 |
+
"group_size": 64,
|
| 29 |
+
"mode": "affine"
|
| 30 |
+
},
|
| 31 |
+
"spatial_merge_size": 2,
|
| 32 |
+
"temperature": 0.15,
|
| 33 |
+
"text_config": {
|
| 34 |
+
"attention_dropout": 0.0,
|
| 35 |
+
"head_dim": 128,
|
| 36 |
+
"hidden_act": "silu",
|
| 37 |
+
"hidden_size": 5120,
|
| 38 |
+
"initializer_range": 0.02,
|
| 39 |
+
"intermediate_size": 32768,
|
| 40 |
+
"max_position_embeddings": 393216,
|
| 41 |
+
"model_type": "ministral3",
|
| 42 |
+
"num_attention_heads": 32,
|
| 43 |
+
"num_hidden_layers": 40,
|
| 44 |
+
"num_key_value_heads": 8,
|
| 45 |
+
"rms_norm_eps": 1e-05,
|
| 46 |
+
"rope_parameters": {
|
| 47 |
+
"beta_fast": 32.0,
|
| 48 |
+
"beta_slow": 1.0,
|
| 49 |
+
"factor": 48.0,
|
| 50 |
+
"llama_4_scaling_beta": 0.1,
|
| 51 |
+
"mscale": 1.0,
|
| 52 |
+
"mscale_all_dim": 1.0,
|
| 53 |
+
"original_max_position_embeddings": 8192,
|
| 54 |
+
"rope_theta": 100000000.0,
|
| 55 |
+
"rope_type": "yarn",
|
| 56 |
+
"type": "yarn"
|
| 57 |
},
|
| 58 |
+
"sliding_window": null,
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 131072
|
| 61 |
+
},
|
| 62 |
+
"tie_word_embeddings": false,
|
| 63 |
+
"transformers_version": "5.0.0.dev0",
|
| 64 |
+
"vision_config": {
|
| 65 |
+
"attention_dropout": 0.0,
|
| 66 |
+
"head_dim": 64,
|
| 67 |
+
"hidden_act": "silu",
|
| 68 |
+
"hidden_size": 1024,
|
| 69 |
+
"image_size": 1540,
|
| 70 |
+
"initializer_range": 0.02,
|
| 71 |
+
"intermediate_size": 4096,
|
| 72 |
+
"model_type": "pixtral",
|
| 73 |
+
"num_attention_heads": 16,
|
| 74 |
+
"num_channels": 3,
|
| 75 |
+
"num_hidden_layers": 24,
|
| 76 |
+
"patch_size": 14,
|
| 77 |
+
"rope_parameters": {
|
| 78 |
+
"rope_theta": 10000.0,
|
| 79 |
+
"rope_type": "default"
|
| 80 |
+
}
|
| 81 |
+
},
|
| 82 |
+
"vision_feature_layer": -1
|
| 83 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
consolidated.safetensors.index.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
CHANGED
|
@@ -3,5 +3,7 @@
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 262144,
|
| 5 |
"pad_token_id": 11,
|
|
|
|
|
|
|
| 6 |
"transformers_version": "5.0.0.dev0"
|
| 7 |
}
|
|
|
|
| 3 |
"eos_token_id": 2,
|
| 4 |
"max_length": 262144,
|
| 5 |
"pad_token_id": 11,
|
| 6 |
+
"do_sample": true,
|
| 7 |
+
"temperature": 0.15,
|
| 8 |
"transformers_version": "5.0.0.dev0"
|
| 9 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4affee474ddbe0f045e9786e0ad5808308b668930dc7c2e13c9a7af00035ed19
|
| 3 |
+
size 5349121606
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5314713080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e86e056f0fd88cb0b2923a69100db9cf791dbce35568859db92b1ae3f9c100af
|
| 3 |
size 5314713080
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c3df3e14a740b6645b3f2973bed704d3c32d5c246e4a586dbbc2c8ac6564c2
|
| 3 |
+
size 4438996692
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
params.json
CHANGED
|
@@ -10,7 +10,6 @@
|
|
| 10 |
"vocab_size": 131072,
|
| 11 |
"tied_embeddings": false,
|
| 12 |
"max_position_embeddings": 393216,
|
| 13 |
-
"max_seq_len": 262144,
|
| 14 |
"llama_4_scaling": {
|
| 15 |
"original_max_position_embeddings": 8192,
|
| 16 |
"beta": 0.1
|
|
|
|
| 10 |
"vocab_size": 131072,
|
| 11 |
"tied_embeddings": false,
|
| 12 |
"max_position_embeddings": 393216,
|
|
|
|
| 13 |
"llama_4_scaling": {
|
| 14 |
"original_max_position_embeddings": 8192,
|
| 15 |
"beta": 0.1
|
processor_config.json
CHANGED
|
@@ -4,8 +4,6 @@
|
|
| 4 |
"image_processor": {
|
| 5 |
"crop_size": null,
|
| 6 |
"data_format": "channels_first",
|
| 7 |
-
"device": null,
|
| 8 |
-
"disable_grouping": null,
|
| 9 |
"do_center_crop": null,
|
| 10 |
"do_convert_rgb": true,
|
| 11 |
"do_normalize": true,
|
|
@@ -17,26 +15,24 @@
|
|
| 17 |
0.4578275,
|
| 18 |
0.40821073
|
| 19 |
],
|
| 20 |
-
"image_processor_type": "
|
| 21 |
"image_seq_length": null,
|
| 22 |
"image_std": [
|
| 23 |
0.26862954,
|
| 24 |
0.26130258,
|
| 25 |
0.27577711
|
| 26 |
],
|
| 27 |
-
"input_data_format": null,
|
| 28 |
"pad_size": null,
|
| 29 |
"patch_size": 14,
|
| 30 |
-
"processor_class": "
|
| 31 |
"resample": 3,
|
| 32 |
"rescale_factor": 0.00392156862745098,
|
| 33 |
-
"return_tensors": null,
|
| 34 |
"size": {
|
| 35 |
"longest_edge": 1540
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"image_token": "[IMG]",
|
| 39 |
"patch_size": 14,
|
| 40 |
-
"processor_class": "
|
| 41 |
"spatial_merge_size": 2
|
| 42 |
}
|
|
|
|
| 4 |
"image_processor": {
|
| 5 |
"crop_size": null,
|
| 6 |
"data_format": "channels_first",
|
|
|
|
|
|
|
| 7 |
"do_center_crop": null,
|
| 8 |
"do_convert_rgb": true,
|
| 9 |
"do_normalize": true,
|
|
|
|
| 15 |
0.4578275,
|
| 16 |
0.40821073
|
| 17 |
],
|
| 18 |
+
"image_processor_type": "PixtralImageProcessor",
|
| 19 |
"image_seq_length": null,
|
| 20 |
"image_std": [
|
| 21 |
0.26862954,
|
| 22 |
0.26130258,
|
| 23 |
0.27577711
|
| 24 |
],
|
|
|
|
| 25 |
"pad_size": null,
|
| 26 |
"patch_size": 14,
|
| 27 |
+
"processor_class": "Mistral3Processor",
|
| 28 |
"resample": 3,
|
| 29 |
"rescale_factor": 0.00392156862745098,
|
|
|
|
| 30 |
"size": {
|
| 31 |
"longest_edge": 1540
|
| 32 |
}
|
| 33 |
},
|
| 34 |
"image_token": "[IMG]",
|
| 35 |
"patch_size": 14,
|
| 36 |
+
"processor_class": "Mistral3Processor",
|
| 37 |
"spatial_merge_size": 2
|
| 38 |
}
|
tekken.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:600bb27946565481ecf51ba8aee252e49b9a68507866080ac9c30185bb312843
|
| 3 |
+
size 16753784
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99cf274236c60277fcfad861a5a1007518687ad06ba8938760f50b55ffa0b1ef
|
| 3 |
+
size 17077420
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": null,
|
| 3 |
"backend": "tokenizers",
|
|
|
|
|
|
|
| 4 |
"extra_special_tokens": [
|
| 5 |
"<unk>",
|
| 6 |
"<s>",
|
|
@@ -36,8 +38,8 @@
|
|
| 36 |
"<SPECIAL_31>",
|
| 37 |
"[ARGS]",
|
| 38 |
"[CALL_ID]",
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
"<SPECIAL_36>",
|
| 42 |
"<SPECIAL_37>",
|
| 43 |
"<SPECIAL_38>",
|
|
@@ -1003,11 +1005,10 @@
|
|
| 1003 |
"<SPECIAL_998>",
|
| 1004 |
"<SPECIAL_999>"
|
| 1005 |
],
|
|
|
|
| 1006 |
"model_max_length": 1000000000000000019884624838656,
|
| 1007 |
-
"bos_token": "<s>",
|
| 1008 |
-
"eos_token": "</s>",
|
| 1009 |
"pad_token": "<pad>",
|
| 1010 |
-
"
|
| 1011 |
-
"
|
| 1012 |
-
"
|
| 1013 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": null,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
"extra_special_tokens": [
|
| 7 |
"<unk>",
|
| 8 |
"<s>",
|
|
|
|
| 38 |
"<SPECIAL_31>",
|
| 39 |
"[ARGS]",
|
| 40 |
"[CALL_ID]",
|
| 41 |
+
"<SPECIAL_34>",
|
| 42 |
+
"<SPECIAL_35>",
|
| 43 |
"<SPECIAL_36>",
|
| 44 |
"<SPECIAL_37>",
|
| 45 |
"<SPECIAL_38>",
|
|
|
|
| 1005 |
"<SPECIAL_998>",
|
| 1006 |
"<SPECIAL_999>"
|
| 1007 |
],
|
| 1008 |
+
"is_local": true,
|
| 1009 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
|
|
|
| 1010 |
"pad_token": "<pad>",
|
| 1011 |
+
"processor_class": "Mistral3Processor",
|
| 1012 |
+
"tokenizer_class": "TokenizersBackend",
|
| 1013 |
+
"unk_token": "<unk>"
|
| 1014 |
}
|