Instructions to use aethertp/PicoLM-V4-85M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aethertp/PicoLM-V4-85M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="aethertp/PicoLM-V4-85M-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aethertp/PicoLM-V4-85M-Instruct")
model = AutoModelForCausalLM.from_pretrained("aethertp/PicoLM-V4-85M-Instruct", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use aethertp/PicoLM-V4-85M-Instruct 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 aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Use Docker

docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use aethertp/PicoLM-V4-85M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aethertp/PicoLM-V4-85M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aethertp/PicoLM-V4-85M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

SGLang

How to use aethertp/PicoLM-V4-85M-Instruct 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 "aethertp/PicoLM-V4-85M-Instruct" \
    --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": "aethertp/PicoLM-V4-85M-Instruct",
		"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 "aethertp/PicoLM-V4-85M-Instruct" \
        --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": "aethertp/PicoLM-V4-85M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use aethertp/PicoLM-V4-85M-Instruct with Ollama:
```
ollama run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use aethertp/PicoLM-V4-85M-Instruct with Docker Model Runner:
```
docker model run hf.co/aethertp/PicoLM-V4-85M-Instruct:Q4_K_M
```

Lemonade

How to use aethertp/PicoLM-V4-85M-Instruct with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aethertp/PicoLM-V4-85M-Instruct:Q4_K_M

Run and chat with the model

lemonade run user.PicoLM-V4-85M-Instruct-Q4_K_M

List all available models

lemonade list

Atomic Chat

PicoLM-V4-85M-Instruct / eval_results.json

aethertp

PicoLM-V4-85M-Instruct: weights, tokenizer, chat template, GGUF, card, evaluation results

fb1ded3 verified 8 days ago

Raw History Blame Contribute Delete

7.42 kB

{
 "mode": "FULL",
 "limit": null,
 "max_len": 1024,
 "batch_size": 32,
 "tasks": [
  "hellaswag",
  "arc_easy",
  "arc_challenge",
  "piqa",
  "winogrande",
  "openbookqa",
  "sciq",
  "boolq",
  "lambada_openai",
  "wikitext"
 ],
 "versions": {
  "lm_eval": "0.4.9.1",
  "transformers": "4.57.1",
  "torch": "2.11.0+cu130",
  "datasets": "3.6.0",
  "tokenizers": "0.22.2",
  "safetensors": "0.8.0",
  "huggingface_hub": "0.36.0"
 },
 "cand": "muon-3e-4",
 "results": {
  "PicoLM-V4-85M-Instruct (muon 3e-4)": {
   "tasks": {
    "hellaswag": {
     "results": {
      "alias": "hellaswag",
      "acc,none": 0.3043218482374029,
      "acc_stderr,none": 0.004591792612775816,
      "acc_norm,none": 0.33588926508663614,
      "acc_norm_stderr,none": 0.004713351500885424
     },
     "version": 1.0,
     "n_samples": {
      "original": 10042,
      "effective": 10042
     }
    },
    "arc_easy": {
     "results": {
      "alias": "arc_easy",
      "acc,none": 0.5505050505050505,
      "acc_stderr,none": 0.010207308833916014,
      "acc_norm,none": 0.49663299663299665,
      "acc_norm_stderr,none": 0.010259550893799069
     },
     "version": 1.0,
     "n_samples": {
      "original": 2376,
      "effective": 2376
     }
    },
    "arc_challenge": {
     "results": {
      "alias": "arc_challenge",
      "acc,none": 0.23122866894197952,
      "acc_stderr,none": 0.01232085883477234,
      "acc_norm,none": 0.257679180887372,
      "acc_norm_stderr,none": 0.012780770562768334
     },
     "version": 1.0,
     "n_samples": {
      "original": 1172,
      "effective": 1172
     }
    },
    "piqa": {
     "results": {
      "alias": "piqa",
      "acc,none": 0.6343852013057671,
      "acc_stderr,none": 0.01123657167900628,
      "acc_norm,none": 0.6235038084874864,
      "acc_norm_stderr,none": 0.011304341550126641
     },
     "version": 1.0,
     "n_samples": {
      "original": 1838,
      "effective": 1838
     }
    },
    "winogrande": {
     "results": {
      "alias": "winogrande",
      "acc,none": 0.500394632991318,
      "acc_stderr,none": 0.01405248130604961
     },
     "version": 1.0,
     "n_samples": {
      "original": 1267,
      "effective": 1267
     }
    },
    "openbookqa": {
     "results": {
      "alias": "openbookqa",
      "acc,none": 0.226,
      "acc_stderr,none": 0.01872295644913999,
      "acc_norm,none": 0.318,
      "acc_norm_stderr,none": 0.020847571620814014
     },
     "version": 1.0,
     "n_samples": {
      "original": 500,
      "effective": 500
     }
    },
    "sciq": {
     "results": {
      "alias": "sciq",
      "acc,none": 0.8,
      "acc_stderr,none": 0.012655439943366653,
      "acc_norm,none": 0.728,
      "acc_norm_stderr,none": 0.014078856992462642
     },
     "version": 1.0,
     "n_samples": {
      "original": 1000,
      "effective": 1000
     }
    },
    "boolq": {
     "results": {
      "alias": "boolq",
      "acc,none": 0.5694189602446483,
      "acc_stderr,none": 0.0086603601459887
     },
     "version": 2.0,
     "n_samples": {
      "original": 3270,
      "effective": 3270
     }
    },
    "lambada_openai": {
     "results": {
      "alias": "lambada_openai",
      "perplexity,none": 56.43329490407561,
      "perplexity_stderr,none": 2.4147160893361925,
      "acc,none": 0.3021540849990297,
      "acc_stderr,none": 0.006397437889678647
     },
     "version": 1.0,
     "n_samples": {
      "original": 5153,
      "effective": 5153
     }
    },
    "wikitext": {
     "results": {
      "alias": "wikitext",
      "word_perplexity,none": 46.20592622522113,
      "word_perplexity_stderr,none": "N/A",
      "byte_perplexity,none": 2.0478907652821867,
      "byte_perplexity_stderr,none": "N/A",
      "bits_per_byte,none": 1.0341387638786332,
      "bits_per_byte_stderr,none": "N/A"
     },
     "version": 2.0,
     "n_samples": {
      "original": 62,
      "effective": 62
     }
    }
   },
   "seconds": 563
  },
  "PicoLM-V4-85M Base (yeniden ko\u015fu)": {
   "tasks": {
    "hellaswag": {
     "results": {
      "alias": "hellaswag",
      "acc,none": 0.30023899621589323,
      "acc_stderr,none": 0.004574250396870965,
      "acc_norm,none": 0.32822146982672773,
      "acc_norm_stderr,none": 0.004686062421158042
     },
     "version": 1.0,
     "n_samples": {
      "original": 10042,
      "effective": 10042
     }
    },
    "arc_easy": {
     "results": {
      "alias": "arc_easy",
      "acc,none": 0.547979797979798,
      "acc_stderr,none": 0.010212436978834194,
      "acc_norm,none": 0.4877946127946128,
      "acc_norm_stderr,none": 0.010256726235129118
     },
     "version": 1.0,
     "n_samples": {
      "original": 2376,
      "effective": 2376
     }
    },
    "arc_challenge": {
     "results": {
      "alias": "arc_challenge",
      "acc,none": 0.22781569965870307,
      "acc_stderr,none": 0.012256708602326964,
      "acc_norm,none": 0.26791808873720135,
      "acc_norm_stderr,none": 0.012942030195136482
     },
     "version": 1.0,
     "n_samples": {
      "original": 1172,
      "effective": 1172
     }
    },
    "piqa": {
     "results": {
      "alias": "piqa",
      "acc,none": 0.6371055495103374,
      "acc_stderr,none": 0.011218667570840779,
      "acc_norm,none": 0.6387377584330794,
      "acc_norm_stderr,none": 0.011207738849429856
     },
     "version": 1.0,
     "n_samples": {
      "original": 1838,
      "effective": 1838
     }
    },
    "winogrande": {
     "results": {
      "alias": "winogrande",
      "acc,none": 0.5011838989739542,
      "acc_stderr,none": 0.014052446290528871
     },
     "version": 1.0,
     "n_samples": {
      "original": 1267,
      "effective": 1267
     }
    },
    "openbookqa": {
     "results": {
      "alias": "openbookqa",
      "acc,none": 0.204,
      "acc_stderr,none": 0.01803936910413861,
      "acc_norm,none": 0.314,
      "acc_norm_stderr,none": 0.020776701920308973
     },
     "version": 1.0,
     "n_samples": {
      "original": 500,
      "effective": 500
     }
    },
    "sciq": {
     "results": {
      "alias": "sciq",
      "acc,none": 0.785,
      "acc_stderr,none": 0.01299784381903183,
      "acc_norm,none": 0.684,
      "acc_norm_stderr,none": 0.014709193056057166
     },
     "version": 1.0,
     "n_samples": {
      "original": 1000,
      "effective": 1000
     }
    },
    "boolq": {
     "results": {
      "alias": "boolq",
      "acc,none": 0.591131498470948,
      "acc_stderr,none": 0.008598573693259202
     },
     "version": 2.0,
     "n_samples": {
      "original": 3270,
      "effective": 3270
     }
    },
    "lambada_openai": {
     "results": {
      "alias": "lambada_openai",
      "perplexity,none": 48.37149598891986,
      "perplexity_stderr,none": 1.9127391398353888,
      "acc,none": 0.3120512322918688,
      "acc_stderr,none": 0.006455101452843129
     },
     "version": 1.0,
     "n_samples": {
      "original": 5153,
      "effective": 5153
     }
    },
    "wikitext": {
     "results": {
      "alias": "wikitext",
      "word_perplexity,none": 38.82775268650654,
      "word_perplexity_stderr,none": "N/A",
      "byte_perplexity,none": 1.982337265879765,
      "byte_perplexity_stderr,none": "N/A",
      "bits_per_byte,none": 0.9872024370038607,
      "bits_per_byte_stderr,none": "N/A"
     },
     "version": 2.0,
     "n_samples": {
      "original": 62,
      "effective": 62
     }
    }
   },
   "seconds": 547
  }
 }
}

	{
	"mode": "FULL",
	"limit": null,
	"max_len": 1024,
	"batch_size": 32,
	"tasks": [
	"hellaswag",
	"arc_easy",
	"arc_challenge",
	"piqa",
	"winogrande",
	"openbookqa",
	"sciq",
	"boolq",
	"lambada_openai",
	"wikitext"
	],
	"versions": {
	"lm_eval": "0.4.9.1",
	"transformers": "4.57.1",
	"torch": "2.11.0+cu130",
	"datasets": "3.6.0",
	"tokenizers": "0.22.2",
	"safetensors": "0.8.0",
	"huggingface_hub": "0.36.0"
	},
	"cand": "muon-3e-4",
	"results": {
	"PicoLM-V4-85M-Instruct (muon 3e-4)": {
	"tasks": {
	"hellaswag": {
	"results": {
	"alias": "hellaswag",
	"acc,none": 0.3043218482374029,
	"acc_stderr,none": 0.004591792612775816,
	"acc_norm,none": 0.33588926508663614,
	"acc_norm_stderr,none": 0.004713351500885424
	},
	"version": 1.0,
	"n_samples": {
	"original": 10042,
	"effective": 10042
	}
	},
	"arc_easy": {
	"results": {
	"alias": "arc_easy",
	"acc,none": 0.5505050505050505,
	"acc_stderr,none": 0.010207308833916014,
	"acc_norm,none": 0.49663299663299665,
	"acc_norm_stderr,none": 0.010259550893799069
	},
	"version": 1.0,
	"n_samples": {
	"original": 2376,
	"effective": 2376
	}
	},
	"arc_challenge": {
	"results": {
	"alias": "arc_challenge",
	"acc,none": 0.23122866894197952,
	"acc_stderr,none": 0.01232085883477234,
	"acc_norm,none": 0.257679180887372,
	"acc_norm_stderr,none": 0.012780770562768334
	},
	"version": 1.0,
	"n_samples": {
	"original": 1172,
	"effective": 1172
	}
	},
	"piqa": {
	"results": {
	"alias": "piqa",
	"acc,none": 0.6343852013057671,
	"acc_stderr,none": 0.01123657167900628,
	"acc_norm,none": 0.6235038084874864,
	"acc_norm_stderr,none": 0.011304341550126641
	},
	"version": 1.0,
	"n_samples": {
	"original": 1838,
	"effective": 1838
	}
	},
	"winogrande": {
	"results": {
	"alias": "winogrande",
	"acc,none": 0.500394632991318,
	"acc_stderr,none": 0.01405248130604961
	},
	"version": 1.0,
	"n_samples": {
	"original": 1267,
	"effective": 1267
	}
	},
	"openbookqa": {
	"results": {
	"alias": "openbookqa",
	"acc,none": 0.226,
	"acc_stderr,none": 0.01872295644913999,
	"acc_norm,none": 0.318,
	"acc_norm_stderr,none": 0.020847571620814014
	},
	"version": 1.0,
	"n_samples": {
	"original": 500,
	"effective": 500
	}
	},
	"sciq": {
	"results": {
	"alias": "sciq",
	"acc,none": 0.8,
	"acc_stderr,none": 0.012655439943366653,
	"acc_norm,none": 0.728,
	"acc_norm_stderr,none": 0.014078856992462642
	},
	"version": 1.0,
	"n_samples": {
	"original": 1000,
	"effective": 1000
	}
	},
	"boolq": {
	"results": {
	"alias": "boolq",
	"acc,none": 0.5694189602446483,
	"acc_stderr,none": 0.0086603601459887
	},
	"version": 2.0,
	"n_samples": {
	"original": 3270,
	"effective": 3270
	}
	},
	"lambada_openai": {
	"results": {
	"alias": "lambada_openai",
	"perplexity,none": 56.43329490407561,
	"perplexity_stderr,none": 2.4147160893361925,
	"acc,none": 0.3021540849990297,
	"acc_stderr,none": 0.006397437889678647
	},
	"version": 1.0,
	"n_samples": {
	"original": 5153,
	"effective": 5153
	}
	},
	"wikitext": {
	"results": {
	"alias": "wikitext",
	"word_perplexity,none": 46.20592622522113,
	"word_perplexity_stderr,none": "N/A",
	"byte_perplexity,none": 2.0478907652821867,
	"byte_perplexity_stderr,none": "N/A",
	"bits_per_byte,none": 1.0341387638786332,
	"bits_per_byte_stderr,none": "N/A"
	},
	"version": 2.0,
	"n_samples": {
	"original": 62,
	"effective": 62
	}
	}
	},
	"seconds": 563
	},
	"PicoLM-V4-85M Base (yeniden ko\u015fu)": {
	"tasks": {
	"hellaswag": {
	"results": {
	"alias": "hellaswag",
	"acc,none": 0.30023899621589323,
	"acc_stderr,none": 0.004574250396870965,
	"acc_norm,none": 0.32822146982672773,
	"acc_norm_stderr,none": 0.004686062421158042
	},
	"version": 1.0,
	"n_samples": {
	"original": 10042,
	"effective": 10042
	}
	},
	"arc_easy": {
	"results": {
	"alias": "arc_easy",
	"acc,none": 0.547979797979798,
	"acc_stderr,none": 0.010212436978834194,
	"acc_norm,none": 0.4877946127946128,
	"acc_norm_stderr,none": 0.010256726235129118
	},
	"version": 1.0,
	"n_samples": {
	"original": 2376,
	"effective": 2376
	}
	},
	"arc_challenge": {
	"results": {
	"alias": "arc_challenge",
	"acc,none": 0.22781569965870307,
	"acc_stderr,none": 0.012256708602326964,
	"acc_norm,none": 0.26791808873720135,
	"acc_norm_stderr,none": 0.012942030195136482
	},
	"version": 1.0,
	"n_samples": {
	"original": 1172,
	"effective": 1172
	}
	},
	"piqa": {
	"results": {
	"alias": "piqa",
	"acc,none": 0.6371055495103374,
	"acc_stderr,none": 0.011218667570840779,
	"acc_norm,none": 0.6387377584330794,
	"acc_norm_stderr,none": 0.011207738849429856
	},
	"version": 1.0,
	"n_samples": {
	"original": 1838,
	"effective": 1838
	}
	},
	"winogrande": {
	"results": {
	"alias": "winogrande",
	"acc,none": 0.5011838989739542,
	"acc_stderr,none": 0.014052446290528871
	},
	"version": 1.0,
	"n_samples": {
	"original": 1267,
	"effective": 1267
	}
	},
	"openbookqa": {
	"results": {
	"alias": "openbookqa",
	"acc,none": 0.204,
	"acc_stderr,none": 0.01803936910413861,
	"acc_norm,none": 0.314,
	"acc_norm_stderr,none": 0.020776701920308973
	},
	"version": 1.0,
	"n_samples": {
	"original": 500,
	"effective": 500
	}
	},
	"sciq": {
	"results": {
	"alias": "sciq",
	"acc,none": 0.785,
	"acc_stderr,none": 0.01299784381903183,
	"acc_norm,none": 0.684,
	"acc_norm_stderr,none": 0.014709193056057166
	},
	"version": 1.0,
	"n_samples": {
	"original": 1000,
	"effective": 1000
	}
	},
	"boolq": {
	"results": {
	"alias": "boolq",
	"acc,none": 0.591131498470948,
	"acc_stderr,none": 0.008598573693259202
	},
	"version": 2.0,
	"n_samples": {
	"original": 3270,
	"effective": 3270
	}
	},
	"lambada_openai": {
	"results": {
	"alias": "lambada_openai",
	"perplexity,none": 48.37149598891986,
	"perplexity_stderr,none": 1.9127391398353888,
	"acc,none": 0.3120512322918688,
	"acc_stderr,none": 0.006455101452843129
	},
	"version": 1.0,
	"n_samples": {
	"original": 5153,
	"effective": 5153
	}
	},
	"wikitext": {
	"results": {
	"alias": "wikitext",
	"word_perplexity,none": 38.82775268650654,
	"word_perplexity_stderr,none": "N/A",
	"byte_perplexity,none": 1.982337265879765,
	"byte_perplexity_stderr,none": "N/A",
	"bits_per_byte,none": 0.9872024370038607,
	"bits_per_byte_stderr,none": "N/A"
	},
	"version": 2.0,
	"n_samples": {
	"original": 62,
	"effective": 62
	}
	}
	},
	"seconds": 547
	}
	}
	}