Instructions to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored")
model = AutoModelForMultimodalLM.from_pretrained("cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored

SGLang

How to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored with Docker Model Runner:
```
docker model run hf.co/cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored
```

Mistral-Medium-3.5-128B-Eschaton-Uncensored

This is a merged BF16 fine-tune of Mistral Medium 3.5 128B. Training loaded the full-BF16 axolotl-ai-co/Mistral-Medium-3.5-128B-BF16 checkpoint and used cloudbjorn/eschaton-uncensored with the Eschaton Engine.

Training used 4-bit NF4 QLoRA with BF16 compute. The resulting LoRA adapter was then merged into the original BF16 base checkpoint, so this repository contains the complete merged BF16 model rather than pre-quantized training weights.

The fine-tune focuses on direct, neutral, and useful responses to sensitive, gritty, controversial, emotionally intimate, and technically demanding prompts without repetitive moralizing or canned disclaimers.

Personality: Objectivity Over Preachiness

The Eschaton Uncensored dataset emphasizes direct answers, task-appropriate tone, technical substance, dark creative work, and candid analysis. It is intended to reduce unnecessary refusals and boilerplate while preserving the broad capabilities of the underlying instruct model.

Model Characteristics

Architecture: Dense 128B Mistral 3 multimodal model
Context window: Up to 262,144 tokens supported by the base architecture
Reasoning modes: Supports Mistral's configurable reasoning behavior
Output format: Complete merged model in BF16
Fine-tuning scope: Text-language layers only; the vision tower and multimodal projector were excluded from LoRA adaptation
Vision behavior: Vision components remain those of the base checkpoint and were not fine-tuned on this text-only dataset

The training sequence length was 2,048 tokens. The base architecture's larger inference context window was not used as the training sequence length for this fine-tune.

Training Details

Parameter	Value
Base model	`axolotl-ai-co/Mistral-Medium-3.5-128B-BF16`
Dataset	`cloudbjorn/eschaton-uncensored`
Framework	Eschaton Engine using Transformers, TRL, PEFT and bitsandbytes
Training method	4-bit NF4 QLoRA
Quantization compute dtype	bfloat16
Double quantization	Enabled
Final repository format	LoRA merged into the BF16 base model
Epochs	1
Training sequence length	2,048 tokens
Packing	Disabled
Seed	3407

LoRA Configuration

The Eschaton Engine automatically selected its 60B–149B model profile for this 127.7B-parameter checkpoint.

Parameter	Value
Rank (`r`)	32
LoRA alpha	64
Target modules	`all-linear` in the language model, excluding vision and multimodal-projector modules
LoRA dropout	0.05
Bias	none
Task type	`CAUSAL_LM`

Optimization

Parameter	Value
Optimizer	8-bit paged AdamW
Per-device micro-batch size	1
Gradient accumulation	32
Effective batch size	32
Learning rate	5e-6
LR scheduler	Linear
Warmup steps	50
Weight decay	0.01
Gradient checkpointing	Enabled

Evaluation Status

No standardized benchmark results are reported for this fine-tune. Users should evaluate it against their own instruction-following, reasoning, coding, safety, and domain-specific requirements before deployment.

License

This derivative follows the base model's Modified MIT License. Review that license and the upstream model card before use or redistribution.

Downloads last month: 32

Safetensors

Model size

128B params

Tensor type

BF16

Model tree for cloudbjorn/Mistral-Medium-3.5-128B-Eschaton-Uncensored

Base model

mistralai/Mistral-Medium-3.5-128B

Finetuned

(11)

this model

Adapters

2 models

cloudbjorn
/

Mistral-Medium-3.5-128B-Eschaton-Uncensored