Instructions to use esilva/KapiCoder-Mongo-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use esilva/KapiCoder-Mongo-Small with Transformers:

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

pipe = pipeline("text-generation", model="esilva/KapiCoder-Mongo-Small")
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("esilva/KapiCoder-Mongo-Small")
model = AutoModelForCausalLM.from_pretrained("esilva/KapiCoder-Mongo-Small", 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

vLLM

How to use esilva/KapiCoder-Mongo-Small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/esilva/KapiCoder-Mongo-Small

SGLang

How to use esilva/KapiCoder-Mongo-Small 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 "esilva/KapiCoder-Mongo-Small" \
    --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": "esilva/KapiCoder-Mongo-Small",
		"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 "esilva/KapiCoder-Mongo-Small" \
        --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": "esilva/KapiCoder-Mongo-Small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use esilva/KapiCoder-Mongo-Small with Docker Model Runner:
```
docker model run hf.co/esilva/KapiCoder-Mongo-Small
```

KapiCoder-Mongo-Small / provenance /model_lock.json

esilva

Add v3 weights (v0.1.0-preview)

4ba57bc verified 2 days ago

Raw History Blame Contribute Delete

4.18 kB

{
  "schema": "kapi-hf-model-lock/1",
  "model": {
    "name": "KapiCoder-Mongo-Small",
    "repo_id": "esilva/KapiCoder-Mongo-Small",
    "generation": "v3",
    "release_tag": "v0.1.0-preview",
    "run": "sft_v3",
    "tier": "T1",
    "status": "PREVIEW (private)"
  },
  "base_model": {
    "repo_id": "Qwen/Qwen2.5-Coder-1.5B",
    "revision": "df3ce67c0e24480f20468b6ef2894622d69eb73b",
    "model_sha256": "8bcb242c05f271406b3f585b7688f86e350413612ef67bca6c61700b22d05f3b",
    "license": "Apache-2.0"
  },
  "weights": {
    "format": "safetensors",
    "dtype": "bfloat16",
    "combined_sha256": "bec5799388cae64e11a1a44a00e253c60743d98d604a21aa2baf2fe122832495",
    "files_sha256": {
      "config.json": "9dd8637a8aaa2eb099a2fbfcc1f3a13c47055b870a850fe807a90f91470165ed",
      "generation_config.json": "444ea57ebf361c659d1f5c23508319b691e181d122588ea3cdd5f68d3e618b1f",
      "merges.txt": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
      "model.safetensors": "93a774dbc3335d85fefc9c11cf595f2a89d80c11177d11f3c85674744ab48108",
      "tokenizer.json": "c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539",
      "tokenizer_config.json": "4a917e4772d9b246ef600e1c5d7d81e3a81ae9f3f2d10d78ccb02c86e5fb184a",
      "vocab.json": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
    }
  },
  "training": {
    "method": "lora",
    "master_dtype": "bf16",
    "optimizer": "adamw",
    "peak_lr": 0.00015,
    "weight_decay": 0.0,
    "seed": 20261018,
    "lora": {
      "r": 64,
      "alpha": 128,
      "dropout": 0.05,
      "targets": [
        "q_proj",
        "k_proj",
        "v_proj",
        "o_proj",
        "gate_proj",
        "up_proj",
        "down_proj"
      ]
    },
    "trainable_params": 73859072,
    "total_steps": 4617,
    "steps_per_epoch": 3078,
    "tokens_seen": 129085790,
    "elapsed_train_h": 15.63,
    "started_utc": "2026-10-25T12:48:11Z",
    "finished_utc": "2026-10-26T04:30:08Z",
    "git_commit": "475159056fd7565f9fac63020ec317e93e1e5b01",
    "git_dirty": false,
    "train_config_sha256": "a45263bbffad55a050a5e8a4a59d361390b7dfb127d86aa07f52bc459d140a1a",
    "config_file_sha256": "20a67dc5334c753dc161cfbade0b8fb6eddf7bc57ff252855981e4731c39847c",
    "libraries": {
      "python": "3.12.10",
      "torch": "2.10.0+rocm7.14.0a20260611",
      "transformers": "4.57.6",
      "peft": "0.17.1",
      "tokenizers": "0.22.2",
      "safetensors": "0.7.0"
    },
    "hardware": "AMD Radeon RX 7800 XT",
    "single_training_run": true
  },
  "dataset": {
    "name": "student corpus v3 (not published)",
    "published": false,
    "label_source": "mixed: teacher_seq (accepted fim_ctx/completion) | gold (llm, grammar, fim_raw) | replay",
    "examples": 309571,
    "tokens_per_epoch": 86000018,
    "replay_examples": 16759,
    "replay_token_share": 0.12,
    "corpus_manifest_sha256": "28ca2cb86c2526db8d5f03dd41c4366c1de98bf54e4f9d5f7b890e7c554589c0",
    "ids_sha256": "22fb98ef1294f5f9e88b0d737074c845afdcb44c771c1683e147c86e2e45b181",
    "rows_sha256": "d9cf6a3ca5a632632e57bc7e03f80dd71b73af71ac171185b985418ba54fd647",
    "student_corpus_config_sha256": "47f02a0b6a2a1564d520c4137715de95932835d143003eb7204b01201f2189fb",
    "accepted_sha256": "2a32311843d3479cfd6ac6210555208bc53d01c19b23887f00a6ab37c1ba97bc"
  },
  "evaluation": {
    "val_v2c": {
      "split": "val",
      "n": 2000,
      "seed": 20261008,
      "sample_ids_sha256": "28ba86be496839a321de0035d6a7e21827a5e8de4362151d80958ee8c798562f",
      "dataset_sha256": "af3331481966f3ebfb05d36109b43014cd850f669f6f5d2a524f8da6e9609ec7",
      "manifest_sha256": "2fef4f342d8a21eaf6d7e9eb1f223b3c8094d56c8dcd00e64f04bc20b20cd3cb"
    },
    "homologation_v1": {
      "set_sha256": "aca0aae51533a95d830c1f296d621f9203a7d76475658fb1e2dcc8f389495332",
      "n": 6030,
      "items_published": false
    },
    "contract": {
      "name": "editor-context-v1",
      "golden_sha256": "06ef5347b128d4dcd11e838ebaa45b30797c5ba30e67222276477e9921ae51c3"
    }
  },
  "publish_tooling": {
    "scripts_publish_sha256": "c31297cc42c0b967e55d196d2e88b48a073d6dc988cd1d097313faafc6b0d45b"
  }
}

	{
	"schema": "kapi-hf-model-lock/1",
	"model": {
	"name": "KapiCoder-Mongo-Small",
	"repo_id": "esilva/KapiCoder-Mongo-Small",
	"generation": "v3",
	"release_tag": "v0.1.0-preview",
	"run": "sft_v3",
	"tier": "T1",
	"status": "PREVIEW (private)"
	},
	"base_model": {
	"repo_id": "Qwen/Qwen2.5-Coder-1.5B",
	"revision": "df3ce67c0e24480f20468b6ef2894622d69eb73b",
	"model_sha256": "8bcb242c05f271406b3f585b7688f86e350413612ef67bca6c61700b22d05f3b",
	"license": "Apache-2.0"
	},
	"weights": {
	"format": "safetensors",
	"dtype": "bfloat16",
	"combined_sha256": "bec5799388cae64e11a1a44a00e253c60743d98d604a21aa2baf2fe122832495",
	"files_sha256": {
	"config.json": "9dd8637a8aaa2eb099a2fbfcc1f3a13c47055b870a850fe807a90f91470165ed",
	"generation_config.json": "444ea57ebf361c659d1f5c23508319b691e181d122588ea3cdd5f68d3e618b1f",
	"merges.txt": "599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3",
	"model.safetensors": "93a774dbc3335d85fefc9c11cf595f2a89d80c11177d11f3c85674744ab48108",
	"tokenizer.json": "c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539",
	"tokenizer_config.json": "4a917e4772d9b246ef600e1c5d7d81e3a81ae9f3f2d10d78ccb02c86e5fb184a",
	"vocab.json": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
	}
	},
	"training": {
	"method": "lora",
	"master_dtype": "bf16",
	"optimizer": "adamw",
	"peak_lr": 0.00015,
	"weight_decay": 0.0,
	"seed": 20261018,
	"lora": {
	"r": 64,
	"alpha": 128,
	"dropout": 0.05,
	"targets": [
	"q_proj",
	"k_proj",
	"v_proj",
	"o_proj",
	"gate_proj",
	"up_proj",
	"down_proj"
	]
	},
	"trainable_params": 73859072,
	"total_steps": 4617,
	"steps_per_epoch": 3078,
	"tokens_seen": 129085790,
	"elapsed_train_h": 15.63,
	"started_utc": "2026-10-25T12:48:11Z",
	"finished_utc": "2026-10-26T04:30:08Z",
	"git_commit": "475159056fd7565f9fac63020ec317e93e1e5b01",
	"git_dirty": false,
	"train_config_sha256": "a45263bbffad55a050a5e8a4a59d361390b7dfb127d86aa07f52bc459d140a1a",
	"config_file_sha256": "20a67dc5334c753dc161cfbade0b8fb6eddf7bc57ff252855981e4731c39847c",
	"libraries": {
	"python": "3.12.10",
	"torch": "2.10.0+rocm7.14.0a20260611",
	"transformers": "4.57.6",
	"peft": "0.17.1",
	"tokenizers": "0.22.2",
	"safetensors": "0.7.0"
	},
	"hardware": "AMD Radeon RX 7800 XT",
	"single_training_run": true
	},
	"dataset": {
	"name": "student corpus v3 (not published)",
	"published": false,
	"label_source": "mixed: teacher_seq (accepted fim_ctx/completion) \| gold (llm, grammar, fim_raw) \| replay",
	"examples": 309571,
	"tokens_per_epoch": 86000018,
	"replay_examples": 16759,
	"replay_token_share": 0.12,
	"corpus_manifest_sha256": "28ca2cb86c2526db8d5f03dd41c4366c1de98bf54e4f9d5f7b890e7c554589c0",
	"ids_sha256": "22fb98ef1294f5f9e88b0d737074c845afdcb44c771c1683e147c86e2e45b181",
	"rows_sha256": "d9cf6a3ca5a632632e57bc7e03f80dd71b73af71ac171185b985418ba54fd647",
	"student_corpus_config_sha256": "47f02a0b6a2a1564d520c4137715de95932835d143003eb7204b01201f2189fb",
	"accepted_sha256": "2a32311843d3479cfd6ac6210555208bc53d01c19b23887f00a6ab37c1ba97bc"
	},
	"evaluation": {
	"val_v2c": {
	"split": "val",
	"n": 2000,
	"seed": 20261008,
	"sample_ids_sha256": "28ba86be496839a321de0035d6a7e21827a5e8de4362151d80958ee8c798562f",
	"dataset_sha256": "af3331481966f3ebfb05d36109b43014cd850f669f6f5d2a524f8da6e9609ec7",
	"manifest_sha256": "2fef4f342d8a21eaf6d7e9eb1f223b3c8094d56c8dcd00e64f04bc20b20cd3cb"
	},
	"homologation_v1": {
	"set_sha256": "aca0aae51533a95d830c1f296d621f9203a7d76475658fb1e2dcc8f389495332",
	"n": 6030,
	"items_published": false
	},
	"contract": {
	"name": "editor-context-v1",
	"golden_sha256": "06ef5347b128d4dcd11e838ebaa45b30797c5ba30e67222276477e9921ae51c3"
	}
	},
	"publish_tooling": {
	"scripts_publish_sha256": "c31297cc42c0b967e55d196d2e88b48a073d6dc988cd1d097313faafc6b0d45b"
	}
	}