Instructions to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT

SGLang

How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT 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 "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT" \
    --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": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT",
		"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 "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT" \
        --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": "AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT with Docker Model Runner:
```
docker model run hf.co/AETHORIA-AI/TR-HASH-MoE-200M-160B-SFT
```

Pacific-i64 commited on 10 days ago

Commit

fce178a

verified ·

1 Parent(s): 122d80e

Add epoch 3 MLX FP16 evaluation export

Browse files

Files changed (7) hide show

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/chat_template.jinja +1 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/chat_template.json +20 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/config.json +28 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/model.safetensors +3 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/special_tokens_map.json +6 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/tokenizer.json +0 -0
training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/tokenizer_config.json +46 -0

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/chat_template.jinja ADDED Viewed

	@@ -0,0 +1 @@

+ {{- "" -}}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{{- "System:\n" + (message['content'] | trim) + "\n\n" -}}{%- elif message['role'] == 'user' -%}{{- "User:\n" + (message['content'] | trim) + "\n\n" -}}{%- elif message['role'] == 'assistant' -%}{{- "Assistant:\n" + (message['content'] | trim) + eos_token -}}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- "Assistant:\n" -}}{%- endif -%}

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/chat_template.json ADDED Viewed

	@@ -0,0 +1,20 @@

+{
+  "assistant_envelope": {
+    "final_end": "\n</final>",
+    "final_start": "\n<final>\n",
+    "scope": "reasoning_tasks",
+    "think_end": "\n</think>",
+    "think_start": "<think>\n",
+    "type": "optional_think_final"
+  },
+  "assistant_only_loss": true,
+  "assistant_prefix": "Assistant:\n",
+  "eos_token": "</s>",
+  "id": "complexity-chat-v2",
+  "system_format": "System:\n{content}\n\n",
+  "system_prompt": "",
+  "training_projection": "naturalize_card_hand_supervise_all_assistant_turns",
+  "turn_separator": "\n\n",
+  "user_format": "User:\n{content}\n\n",
+  "version": 2
+}

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/config.json ADDED Viewed

	@@ -0,0 +1,28 @@

+{
+  "model_type": "complexity",
+  "vocab_size": 32000,
+  "mlp_type": "token_routed",
+  "norm_eps": 1e-06,
+  "shared_expert": true,
+  "use_shared_routed_gates": false,
+  "num_attention_heads": 14,
+  "num_experts": 4,
+  "top_k": 2,
+  "rope_theta": 10000.0,
+  "shared_intermediate_size": 3072,
+  "top_k_primary_weight": 0.5,
+  "num_key_value_heads": 2,
+  "num_hidden_layers": 16,
+  "learn_hash_channel_modulation": false,
+  "route_hash_count": 2,
+  "routing_strategy": "token_id_multi_hash",
+  "use_qk_norm": true,
+  "hidden_size": 896,
+  "max_position_embeddings": 2048,
+  "intermediate_size": 256,
+  "routed_output_scale": 2.0,
+  "hash_channel_scale_init": 0.0,
+  "tie_word_embeddings": true,
+  "shared_output_scale": 1.0,
+  "rope_traditional": false
+}

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a0150dd416ff56fcccd42381831b129d2ff94dceb3225a2c61e682d9aa2c067f
+size 408560864

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

training/sft-v2-300k/checkpoints/step_005982/mlx-fp16/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}