Instructions to use armand0e/Muse-Glimmer-30B-Fable-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use armand0e/Muse-Glimmer-30B-Fable-Distill with Transformers:

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

pipe = pipeline("image-text-to-text", model="armand0e/Muse-Glimmer-30B-Fable-Distill")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("armand0e/Muse-Glimmer-30B-Fable-Distill")
model = AutoModelForMultimodalLM.from_pretrained("armand0e/Muse-Glimmer-30B-Fable-Distill", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use armand0e/Muse-Glimmer-30B-Fable-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "armand0e/Muse-Glimmer-30B-Fable-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "armand0e/Muse-Glimmer-30B-Fable-Distill",
		"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/armand0e/Muse-Glimmer-30B-Fable-Distill

SGLang

How to use armand0e/Muse-Glimmer-30B-Fable-Distill 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 "armand0e/Muse-Glimmer-30B-Fable-Distill" \
    --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": "armand0e/Muse-Glimmer-30B-Fable-Distill",
		"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 "armand0e/Muse-Glimmer-30B-Fable-Distill" \
        --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": "armand0e/Muse-Glimmer-30B-Fable-Distill",
		"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 armand0e/Muse-Glimmer-30B-Fable-Distill with Docker Model Runner:
```
docker model run hf.co/armand0e/Muse-Glimmer-30B-Fable-Distill
```

Muse-Glimmer-30B-Fable-Distill

meta-models/Muse-Glimmer-30B fine-tuned on agentic coding traces and chat distilled from Claude Fable 5, with a multilingual slice. Merged bf16 weights, drop-in for the base: same architecture (text decoder + vision tower), same tokenizer, same chat template, and the base's processor_config.json so AutoProcessor / image input work as in the base (verified after merging with an image request). Only the language model was trained.

The LoRA adapter this was merged from is published separately as armand0e/Muse-Glimmer-30B-Fable-Distill-LoRA.

Chat format and serving

Muse Glimmer uses its own harmony-style "Onyx ATEM" format — reasoning on a <|start|>assistant to=self<|message|>…<|eom|> channel, tool calls as <atem:function_calls> XML, tool results as <tool_output> blocks, <|eot|> end-of-turn. The chat template drives all of it (reasoning_strength: low/medium/high/xhigh, default high; tool-call arguments must be a dict, not a JSON string).

No stock vLLM (≤ 0.28) reasoning or tool parser matches this format — do not enable --reasoning-parser / --tool-call-parser with a stock name (gptoss, hermes, …), they will mis-parse. Serve without parsers (channel markers arrive in content) or register custom parser plugins. Requires transformers ≥ 5.15 (the muse_glimmer architecture ships in the library); with vLLM 0.26 use --model-impl transformers.

vllm serve armand0e/Muse-Glimmer-30B-Fable-Distill \
  --served-model-name muse-glimmer-fable \
  --model-impl transformers \
  --max-model-len 65536 --dtype bfloat16 \
  --override-generation-config '{"temperature": 1.0, "top_p": 0.95, "top_k": 64}'

Training data

651 examples / 3.62M tokens after rendering at a 24,576-token context (trim_followups; median 1.1k tokens, p90 20.4k). Prepared with teich 0.3.6 plus a format patch for this chat format. Reasoning kept and supervised. Rows without any assistant reasoning were rendered at reasoning_strength: low, rows with reasoning at high, so the strength flag in the system prompt actually predicts whether a reasoning channel follows (a first run rendered everything at high and learned to skip thinking). Harness text recorded as assistant turns in the raw sessions (API Error: …, Please run /login …, No response requested.) was removed before rendering — the first run memorised it verbatim. Supervision is scoped so the base's think-first routing survives: on rows without reasoning the initial routing header ( to=user<|message|> / to=<fn><|message|>) is left unsupervised and only the answer or <atem:function_calls> block is trained; on rows with reasoning the headers after <|eom|> are supervised, and the <|start|>assistant continuation that follows every <|eom|> is supervised so thinking → answer is learnable. (A run that supervised every routing header stopped opening the reasoning channel even at xhigh and called tools 1/4 vs the base's 4/4.)

source	description
Fable chat (multilingual)	353 English + 106 translated chats (es/fr/de/pt/ja/zh)
`armand0e/claude-fable-5-claude-code`	Claude Code agent traces
`yellowbeeblackbee/claude-traces`	Claude Code agent traces
`TeichAI/Fable-5-Cursor-Traces`	Cursor agent traces (English)
personal-fable / glint-fable	raw Claude Code sessions, plus ~30% with user/assistant text translated

Validated over every row before training: final answers supervised as to=user<|message|>…<|eot|>, reasoning as to=self<|message|>…<|eom|>, tool calls as recipient header + full <atem:function_calls> block + terminator; user/system/tool-output masked; 40% of tokens supervised.

Training

QLoRA on unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit (NF4), LoRA r=32 / α=32 on the 416 text-decoder projections (self_attn.{q,k,v,o,gate}_proj, mlp.{gate,up,down}_proj; 209.6M parameters), merged into the bf16 base. 24,576-token context, LR 8e-5 linear, 2 epochs (164 steps), batch 1 × grad-accum 8, paged_adamw_8bit, max_grad_norm 0.3, single 64 GB GPU. Fused linear cross-entropy reproducing the model's output_multiplier pre-scale and tanh soft-cap (T=20), verified equal to the model's own loss. Base-model loss on this data at step 1: 1.17.

Limitations

Non-English is ~10% of tokens. Not benchmarked against an answers-only variant. The adapter was trained against NF4 base weights and merged into bf16 — standard QLoRA practice, but the merged model is not bit-identical to what training saw.

Downloads last month: 20

Safetensors

Model size

30B params

Tensor type

BF16

Model tree for armand0e/Muse-Glimmer-30B-Fable-Distill

Base model

meta-models/Muse-Glimmer-30B

Finetuned

(38)

this model