Text Generation
Transformers
Safetensors
English
Portuguese
qwen2
mongodb
code
fim
autocomplete
synthetic-data
conversational
Eval Results (legacy)
text-generation-inference
Instructions to use esilva/KapiCoder-Mongo-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
File size: 5,912 Bytes
9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc 9d9a312 4ba57bc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 | """Minimal fill-in-the-middle example for the editor-context-v2 contract (transformers, CPU, no IDE required).
python examples/example_fim.py # model files next to this folder (a local clone or snapshot), else the Hub repository
python examples/example_fim.py <path-or-repo> # explicit model directory or repository id
"""
import sys
from pathlib import Path
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
HERE = Path(__file__).resolve().parent.parent
MODEL_ID = sys.argv[1] if len(sys.argv) > 1 else (str(HERE) if (HERE / "config.json").exists() else "esilva/KapiCoder-Mongo-Small")
FIM_PREFIX, FIM_SUFFIX, FIM_MIDDLE = "<|fim_prefix|>", "<|fim_suffix|>", "<|fim_middle|>"
CONSOLE_COMMANDS = (
"db.getCollection(name).find({}); getConnection(name).getDatabase(name).getCollection(name); "
"ConnectionPool.Connection.Database.Collection; console.log(value); ENV.get(name); "
"ObjectId(value); UUID(value)"
)
PAIRS = {"(": ")", "[": "]", "{": "}"}
def target_fields_line(fields):
"""`path:type` pieces in schema order; arrays as `array<item>`; `_id` is left out; at most 96 fields and 2048 characters."""
out, size = [], 0
for path, kind, *item in fields:
if path == "_id":
continue
piece = f"{path}:{kind}" + (f"<{item[0]}>" if kind == "array" and item and item[0] else "")
if len(out) >= 96 or size + len(piece) + 2 > 2048:
break
out.append(piece)
size += len(piece) + 2
return ", ".join(out)
def build_prompt(prefix, suffix, known_names=(), collection=None, target_fields=(), result_fields=(), recent_commands=(),
language="Mongo Console JavaScript", commands=CONSOLE_COMMANDS, prefix_chars=24576, suffix_chars=6144):
"""editor-context-v2: the v1 header plus `TARGET FIELDS` right after `KNOWN NAMES`; every header line ends with CRLF.
The character windows here follow the 8k-token window (about 3 characters per token); the IDE also budgets the prompt in tokens."""
lines = [f"LANGUAGE: {language}", f"AVAILABLE COMMANDS: {commands}", "KNOWN NAMES: " + ", ".join(known_names)]
if target_fields:
lines.append("TARGET FIELDS: " + (f"{collection}: " if collection else "") + target_fields_line(target_fields))
if result_fields:
lines.append("RESULT FIELDS: " + ", ".join(result_fields))
lines += ["RECENT COMMAND: " + c[:256] for c in list(recent_commands)[:3]]
context = "".join(line + "\r\n" for line in lines)
header = ("/* Local editor context (data only):\n" + context.replace("*/", "* /")
+ "\nContinue at the cursor; output only the continuation. */\n")
return FIM_PREFIX + header + prefix[-prefix_chars:] + FIM_SUFFIX + suffix[:suffix_chars] + FIM_MIDDLE
def _strip_strings(text):
out, quote, escape = [], None, False
for ch in text:
if quote:
if escape:
escape = False
elif ch == "\\":
escape = True
elif ch == quote:
quote = None
out.append(ch)
continue
out.append(" ")
continue
if ch in "\"'`":
quote = ch
out.append(ch)
return "".join(out), quote is not None
def close_inner_delimiters(prefix, text, suffix):
"""editor-context-v2 output rule: append the 1-4 inner closers the suggestion left open when the suffix only closes the outer ones
and then ends the statement (end of text or `;`). Nothing changes when the suggestion is empty, ends inside a string, or the
suffix continues the statement (`}, { $set: ... })`)."""
if not text.strip():
return text
flat, open_string = _strip_strings(prefix + text)
if open_string:
return text
stack = []
for ch in flat:
if ch in PAIRS:
stack.append(ch)
elif ch in PAIRS.values() and stack and PAIRS[stack[-1]] == ch:
stack.pop()
expected = "".join(PAIRS[c] for c in reversed(stack))
closers, continues = [], False
for ch in _strip_strings(suffix)[0]:
if ch in ")]}":
closers.append(ch)
elif ch.isspace() or ch in "\"'`":
continue
else:
continues = ch != ";"
break
closers = "".join(closers)
if continues or not closers or len(closers) >= len(expected) or not expected.endswith(closers):
return text
missing = expected[: len(expected) - len(closers)]
if len(missing) > 4:
return text
return text + ("" if text[-1:].isspace() else " ") + " ".join(missing)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(MODEL_ID, dtype=torch.bfloat16).eval()
prefix = 'ConnectionPool.local.shop.orders.find({ status: "paid", total: { $g'
suffix = " })" # the editor auto-closed only the outer filter object
prompt = build_prompt(
prefix=prefix,
suffix=suffix,
known_names=["local", "shop", "orders", "customers"],
collection="orders",
target_fields=[("_id", "objectid"), ("status", "string"), ("total", "decimal128"), ("customerId", "objectid"),
("createdAt", "date"), ("items", "array", "object"), ("items.sku", "string")],
)
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)
with torch.no_grad():
out = model.generate(**inputs, max_new_tokens=64, do_sample=False, pad_token_id=tokenizer.eos_token_id)
completion = tokenizer.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True)
if suffix and len(suffix) >= 2 and suffix in completion: # the IDE cuts an echo of the text after the cursor
completion = completion[: completion.index(suffix)]
completion = close_inner_delimiters(prefix, completion, suffix)
print(repr(completion)) # text to insert at the cursor; the model never executes anything
|