Instructions to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Transformers:

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

pipe = pipeline("text-generation", model="kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4")
model = AutoModelForCausalLM.from_pretrained("kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Use Docker

docker model run hf.co/kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

LM Studio
Jan

vLLM

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

SGLang

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 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 "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4" \
    --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": "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4" \
        --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": "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Ollama:
```
ollama run hf.co/kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
```
Unsloth Desktop

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Docker Model Runner:
```
docker model run hf.co/kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M
```

Lemonade

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Run and chat with the model

lemonade run user.loggenix-moe-0.4B-0.2A-sft-s4-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

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 kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M

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 "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

loggenix-moe-0.4B-0.2A-sft-s4

MoE for OpenTelemetry trace analysis and agent-coding observability. 390.1M total / 191.9M active per token (16 experts, top-2), vocab 151,936.

Counted from the weights, not derived from config:

component	params
experts (all 16 x 12 layers)	226.5M
embeddings + LM head	155.6M
attention	7.9M
norms / router gates	0.1M
total	390.1M
active per token (embed + attn + 2 of 16 experts)	191.9M
active excluding embed/head	36.3M

The last row is the one that sets expectations: embeddings are 40% of the model and 81% of the "active" count, but they are a lookup. Only ~36M parameters actually compute per token.

SFT'd from …-sft-s3.1 on TraceVerse observability corpora. Emits structured tool-call JSON against <trace> payloads.

Results

	value
eval_loss	1.365
eval token accuracy	0.750
train_loss	1.44

train_loss > eval_loss, i.e. no overfitting. Nine consecutive eval improvements; the early-stopping gate (patience 3 on eval_loss) never fired.

Scored on the goldens

LLM-as-judge (gpt-oss-120b, rubric-anchored, untruncated, with the session trace in context), on the 142-row held-out agent-coding golden. contract% is a deterministic task-aware check of the output contract -- no model involved.

	Acc	Comp	Fmt	Gnd	Overall	contract%	think%
`…-sft-s3.1` (base)	1.01	1.01	1.00	1.00	1.01	0%	0%
this model @ 1.4 ep	2.20	2.60	5.07	2.27	2.78	88%	92%
this model (2.4 ep)	2.25	2.69	5.34	2.39	2.87	88%	96%

General-purpose golden (218 rows): 1.71. The drop is the specialisation showing -- Format falls 5.34 → 2.43 off-domain.

Read the shape of this, not just the number. Format 5.34 against Accuracy 2.25 says the model learned the output contract almost completely and the substance far less. Contract adherence went 0% → 88% from SFT. For comparison on the same golden, gpt-oss-120b scores near the top on judge overall with 0% contract adherence -- it writes good prose that ignores the required output shape entirely. If you are consuming structured output, that difference matters more than the overall gap suggests.

Usage — transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

REPO = "kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4"
tok = AutoTokenizer.from_pretrained(REPO, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    REPO, dtype=torch.bfloat16, trust_remote_code=True
).eval().cuda()

messages = [
    {"role": "system", "content": "You are a TraceVerse observability analyst."},
    {"role": "user", "content": (
        "Which MCP tools should be called to diagnose this? Respond with a JSON array.\n\n"
        '<trace>[{"service":"checkout-api","child":"payment-svc",'
        '"http.status_code":503,"duration_ms":4200}]</trace>'
    )},
]

enc = tok.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
)
# apply_chat_template returns a BatchEncoding, not a tensor -- index input_ids.
ids = (enc["input_ids"] if hasattr(enc, "keys") else enc).to(model.device)

out = model.generate(
    ids,
    max_new_tokens=1500,        # NOT 128. This model reasons before answering;
                                # a low budget truncates it mid-thought.
    do_sample=True,             # NOT greedy -- greedy decoding sends this model
    temperature=0.7,            # into repetition loops. Measured, not theoretical.
    top_p=0.95,
    top_k=20,
)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))

Two settings that matter more than usual

Do not use greedy decoding. With do_sample=False this model degenerates into repetition loops. With temperature=0.7 / top_p=0.95 / top_k=20 it produces clean structured output. This is a measured difference on identical prompts, and it matches vendor guidance for the Qwen3 family generally.

Give it enough tokens. 400 was not enough to finish a response in testing; 1,500 is a safe floor. Truncation mid-reasoning looks like incoherence but is not.

Prompt shape

Trained on <trace>-grounded prompts with a system role. Bare questions with no trace payload are out of distribution and degrade noticeably.

Usage — GGUF / ollama

Three quantisations under gguf/:

file	size	measured
`…-f16.gguf`	786 MB	218 tok/s
`…-Q8_0.gguf`	421 MB	—
`…-Q4_K_M.gguf`	256 MB	344 tok/s

Q4_K_M is ~1.6x faster than f16 with no quality degradation observed on structured-output prompts.

ollama create loggenix-s4 -f gguf/Modelfile.Q4_K_M
ollama run loggenix-s4

The bundled Modelfiles set num_ctx 8192 — matching the training context. Do not drop this to 4096: trace payloads routinely exceed it and llama.cpp truncates the prompt silently, so the model answers on a partial trace with no error raised.

`norm_topk_prob`

This checkpoint is trained with norm_topk_prob=true. llama.cpp's qwen3moe graph hardcodes norm_w=true and ignores the GGUF expert_weights_norm key, so a checkpoint trained with false converts to a GGUF that produces garbage on every llama.cpp runtime. That setting is why these GGUFs are coherent.

Training


Base	`loggenix-moe-0.4B-0.2A-sft-s3.1`
Method	TRL `SFTTrainer`, full fine-tune (LoRA does not work for MoE)
Precision / attn	bf16 / FlashAttention-2
Sequence	8192, packing enabled
Batch	1 x grad-accum 8 = 65,536 tokens/step
LR	2e-4, cosine, warmup ratio 0.1
Hardware	1x RTX 5090 (24 GB)

Corpus

source	rows	share
`TraceVerse-RL-SFT-AgentMix3`	49,017	61.9%
`TraceVerse-RL-SFT-Clean`	18,303	23.1%
`loggenix-stage4-sft-dataset` (synthetic)	11,880	15.0%
total	79,200	2,000 held out for eval

100% observability domain, filtered to n_tokens <= 8192.

Limitations

Specialist. Trained on trace analysis and tool-calling; general capability is not a target and will be weak.
Synthetic data is 15% of rows.
Accuracy and Grounding are the weak axes (2.25 / 2.39 against Format 5.34). It reliably produces well-formed answers that are often not the right answer. Do not deploy it as an autonomous analyst; it is suited to structured extraction and first-pass triage where the shape is the hard part and a human or a stronger model checks the content.
Off-domain use is not supported. The general-golden score (1.71, Format 2.43) is what happens outside trace analysis.
Scores above come from an LLM judge and carry its noise. The contract% column does not -- it is deterministic and is the number to trust for format claims.

Downloads last month: 1,662

Safetensors

Model size

0.4B params

Tensor type

BF16

Model tree for kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s4

Base model

kshitijthakkar/loggenix-moe-0.4B-0.2A-sft-s3.1

Quantized

(1)

this model

Finetunes

1 model