rockerritesh/r1-distill-qwen7b-offline
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: rockerritesh/r1-distill-qwen7b-offline
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-28 20:09:19 +08:00
commit 71a5ff9c45
13 changed files with 1464 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

7
README.md Normal file
View File

@@ -0,0 +1,7 @@
---
license: mit
---
# R1-Distill-Qwen-7B-AWQ — offline inference bundle
AWQ 4-bit reasoning model with a self-contained script.py that runs fully offline (loads from `.`). Reasons step by step, then emits a final JSON array. Fits a 16 GB GPU.

38
config.json Normal file
View File

@@ -0,0 +1,38 @@
{
"_name_or_path": "/root/.cache/huggingface/hub/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-7B/snapshots/008b8c2e0b59dac9b7619d58a5ad609f43a5b6b1",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.1",
"use_cache": false,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
}

8
generation_config.json Normal file
View File

@@ -0,0 +1,8 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": 151643,
"transformers_version": "4.47.1",
"use_cache": false
}

1
harness_cfg.json Normal file
View File

@@ -0,0 +1 @@
{"cot": true, "max_new_cap": 1536}

292
iol_harness.py Normal file
View File

@@ -0,0 +1,292 @@
"""Pure-Python harness logic for the IOL-AI 2026 submission.
Kept free of torch/transformers so it can be unit-tested locally without a GPU
or the model. ``script.py`` (which runs on the T4) imports from here; so does
``test_parsing.py``. Both this file and ``script.py`` are uploaded to the
submission repo, so ``import iol_harness`` resolves at run time (the repo root is
the working directory and on sys.path[0]).
"""
import ast
import json
import re
# --------------------------------------------------------------------------- #
# Item counting
# --------------------------------------------------------------------------- #
# "17. ", "18) ", ... anywhere after start/space/comma/semicolon, followed by
# whitespace or end-of-line. Requires whitespace after the . or ) so decimals
# like "3.14" are NOT matched.
_NUMBERED = re.compile(r"(?:^|[\s,;])(\d{1,3})[.)](?=\s|$)", re.MULTILINE)
# "(1)", "(2)" — parenthesised single number. "(1-2)" is NOT matched.
_PAREN = re.compile(r"\((\d{1,3})\)")
# Explicit item range in the query, e.g. "(1-9)", "(13–16)", "(1—10)".
_RANGE = re.compile(r"\((\d{1,3})\s*[-–—]\s*(\d{1,3})\)")
def _distinct(rx, text):
return sorted(set(int(x) for x in rx.findall(text or "")))
def _range_count(query):
"""Count from an explicit "(a-b)" range in the query, else 0."""
best = 0
for a, b in _RANGE.findall(query or ""):
a, b = int(a), int(b)
if b >= a:
best = max(best, b - a + 1)
return best
def _item_lines(query):
"""Non-empty lines after the first non-empty (instruction) line."""
lines = [ln for ln in (query or "").splitlines() if ln.strip()]
return max(0, len(lines) - 1)
def count_items(context, query, task_type=""):
"""How many answers the problem expects (validated on real Linguini data).
Items live in different places by task type: numbered/bare lines in the
query, blanks "(N)" or a numbered list in the context, or an explicit
"(a-b)" range in the query. Returns an int >= 1. Biased so that when in
doubt it does not under-count (the scorer ignores extra predictions but
zero-scores any item a short prediction fails to cover).
"""
tt = (task_type or "").strip()
# 1. An explicit range in the query is the strongest, cleanest signal.
r = _range_count(query)
if r:
return r
qn, qp = _distinct(_NUMBERED, query), _distinct(_PAREN, query)
cn, cp = _distinct(_NUMBERED, context), _distinct(_PAREN, context)
il = _item_lines(query)
if tt in ("text_to_num", "num_to_text"):
# numbers/words listed as bare lines after the instruction line
return max(il, len(qn), len(qp), 1)
if tt == "match_letters":
# items numbered in the query if present, else numbered in the context
return len(qn) or len(cn) or il or 1
if tt == "fill_blanks":
return max(len(qp), len(qn), len(cp), il, 1)
# translation / default
n = max(len(qn), len(qp))
if n <= 1:
# bare item lines in the query, else blanks enumerated in the context
n = il if il >= 1 else max(len(cp), 1)
return max(n, 1)
# --------------------------------------------------------------------------- #
# Prompt building (task-type aware)
# --------------------------------------------------------------------------- #
SYSTEM_BASE = (
"You are an expert solver of International Linguistics Olympiad (IOL) "
"problems. Every problem is fully self-contained: use ONLY the data, "
"examples and hints given to deduce the grammar, vocabulary and rules of "
"the language. Never rely on outside knowledge of the language — work the "
"pattern out from the given data. First reason it out silently, then answer "
"every numbered item.\n"
"OUTPUT FORMAT: respond with ONLY a JSON array of strings — one string per "
"numbered item, in the SAME order as the query. No keys, no numbering, no "
"commentary, nothing outside the array."
)
_TASK_GUIDANCE = {
"translation": (
"Each answer is the translation of that item, using the vocabulary and "
"grammar you deduced from the data. Answer in the language the query "
"names: 'into English' -> English; 'into <language>' -> that language. "
"Output only the translated text."
),
"fill_blanks": (
"Work out the rule from the complete rows, then fill each blank with the "
"missing form IN THE LANGUAGE BEING ANALYSED (the non-English / target "
"language) — never its English meaning. Output only that form."
),
"match_letters": (
"For each numbered item, output ONLY the single UPPERCASE LETTER "
"(A, B, C, ...) of its correct match. Never output the matched word, its "
"translation, or any text other than the letter."
),
"text_to_num": (
"Work out the number system from the examples, then COMPUTE each value "
'and write it in digits (e.g. "285"). Do NOT copy a number from the '
"examples — derive the value for each new item. Output only the digits."
),
"num_to_text": (
"Work out the number system from the examples, then CONSTRUCT each number "
"as words in the target (task) language using those rules. Do NOT copy an "
"example — build the form for the given number. Output only those words."
),
}
_TASK_GUIDANCE_DEFAULT = (
"Give exactly what each numbered item asks for, in the form the query "
"requests."
)
def task_guidance(task_type):
return _TASK_GUIDANCE.get((task_type or "").strip(), _TASK_GUIDANCE_DEFAULT)
SYSTEM_COT = (
"You are an expert solver of International Linguistics Olympiad (IOL) "
"problems. Every problem is self-contained: use ONLY the given data to deduce "
"the language's rules — never outside knowledge of the language. Reason "
"step by step to work out the pattern, then give your answers.\n"
"FINAL LINE: after your reasoning, output ONLY a JSON array of strings — one "
"per numbered item, in order — as the very last thing in your reply."
)
def build_messages(context, query, task_type, n, cot=False):
"""Return chat messages. ``n`` = required answer count. ``cot`` = let the
model reason before emitting the final JSON array (for reasoning models)."""
base = SYSTEM_COT if cot else SYSTEM_BASE
system = (
f"{base}\n{task_guidance(task_type)}\n"
f"The JSON array must have EXACTLY {n} string{'s' if n != 1 else ''}."
)
tail = (
f"Answer all {n} item{'s' if n != 1 else ''} as a JSON array of "
f"{n} string{'s' if n != 1 else ''}, in order"
+ (", after your step-by-step reasoning." if cot else ".")
)
user = f"{(context or '').strip()}\n\n{(query or '').strip()}\n\n{tail}"
return [
{"role": "system", "content": system},
{"role": "user", "content": user},
]
def max_new_tokens_for(task_type, n, cot=False, cap=1024):
"""Heuristic generation budget. ``cot`` adds room for reasoning (bounded by
``cap`` to protect the 30-min limit on a T4)."""
per_item = 96 if (task_type or "") == "translation" else 40
answer_room = 160 + per_item * max(1, n)
if cot:
return int(min(cap, answer_room + 640))
return int(min(cap, answer_room))
# --------------------------------------------------------------------------- #
# Answer parsing (robust, multi-layer)
# --------------------------------------------------------------------------- #
_FENCE = re.compile(r"```(?:json|python)?\s*(.*?)```", re.DOTALL | re.IGNORECASE)
_LINE_NUM = re.compile(r"^\s*[\(\[]?(\d{1,3})[\).\]:]\s*(.*\S)?\s*$")
_PREFIX = re.compile(r"^\s*(?:answers?|output|result)\s*[:\-]\s*", re.IGNORECASE)
def _to_str(x):
if x is None:
return ""
if isinstance(x, (list, tuple)):
# A nested item (e.g. multiple accepted forms) — join readably.
return " ".join(_to_str(e) for e in x)
return str(x)
def _strip_quotes(s):
s = s.strip()
if len(s) >= 2 and s[0] == s[-1] and s[0] in "\"'`":
s = s[1:-1].strip()
return s
def _clean(s):
return _strip_quotes(_to_str(s).strip())
def _strip_fences(text):
m = _FENCE.search(text or "")
return m.group(1) if m else (text or "")
def _balanced_arrays(text):
"""Yield every top-level [...] substring (handles nesting)."""
depth, start = 0, -1
for i, ch in enumerate(text):
if ch == "[":
if depth == 0:
start = i
depth += 1
elif ch == "]" and depth > 0:
depth -= 1
if depth == 0 and start >= 0:
yield text[start : i + 1]
def extract_json_array(text):
"""Return the LAST bracketed list that parses, as a list of strings, else None.
'Last' matters for reasoning models: they emit <think>...</think> (often
containing brackets) and then the final answer array — we want that final one.
"""
if not text:
return None
for frag in reversed(list(_balanced_arrays(text))):
for parser in (json.loads, ast.literal_eval):
try:
value = parser(frag)
except Exception:
continue
if isinstance(value, list):
return [_clean(x) for x in value]
return None
def parse_numbered_lines(text):
"""Parse 'N. answer' / 'N) answer' / '(N) answer' lines -> ordered answers."""
found = {}
for line in (text or "").splitlines():
m = _LINE_NUM.match(line)
if m and m.group(2):
found[int(m.group(1))] = _clean(m.group(2))
if not found:
return []
return [found[k] for k in sorted(found)]
def _fit(values, n):
"""Force ``values`` to exactly ``n`` entries (truncate / pad with '')."""
values = list(values)[:n]
values += [""] * (n - len(values))
return values
def parse_answers(text, n):
"""Turn raw model output into exactly ``n`` cleaned answer strings.
Layers: JSON array -> numbered lines -> plain non-empty lines. Always
returns a list of length ``n``; extras are dropped, shortfalls padded so no
item is silently missing (the scorer aligns predictions by position).
"""
n = max(1, int(n))
inner = _strip_fences(text)
# Reasoning models wrap their scratch-work in <think>...</think>; the answer
# follows the closing tag. Keep only what comes after it.
if "</think>" in inner:
inner = inner.rsplit("</think>", 1)[1]
arr = extract_json_array(inner)
if arr:
return _fit(arr, n)
numbered = parse_numbered_lines(inner)
if numbered:
return _fit(numbered, n)
lines = [_clean(_PREFIX.sub("", ln)) for ln in inner.splitlines()]
lines = [ln for ln in lines if ln]
if lines:
return _fit(lines, n)
single = _clean(inner)
return _fit([single] if single else [], n)

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:27607ecb3f635669ed627bcc473d89e8fb0ee04a8ba50bd7ee9249a089412cf3
size 4480835056

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7946740ab848b4a02904f05bff81211bf9600fc20bfad39bbcc8d1703a40ce1c
size 1089994880

738
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,738 @@
{
"metadata": {
"total_size": 5570747392
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
"model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00001-of-00002.safetensors",
"lm_head.weight": "model-00002-of-00002.safetensors"
}
}

117
script.py Normal file
View File

@@ -0,0 +1,117 @@
"""IOL-AI 2026 submission entrypoint.
Runs on the platform's T4 (16 GB), offline, within a 30-minute limit. Reads the
hidden test set from /tmp/data/test.csv and writes submission.csv (id,pred) to
the working directory. Model weights ship inside this repo and load from ".".
Baseline model: Qwen/Qwen2.5-1.5B-Instruct. The score lever here is the harness
(task-aware prompts + robust parsing) in iol_harness.py, not the model size.
"""
import os
import time
# Must be set BEFORE importing transformers: no network at run time.
os.environ["HF_HUB_OFFLINE"] = "1"
os.environ["TRANSFORMERS_OFFLINE"] = "1"
os.environ.setdefault("TOKENIZERS_PARALLELISM", "false")
import json
import pandas as pd
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import iol_harness as H
MODEL_ID = "." # weights are shipped in this repo (offline)
TEST_CSV = "/tmp/data/test.csv"
OUT_CSV = "submission.csv"
TIME_LIMIT_S = 30 * 60
SAFETY_S = 26 * 60 # stop generating past this; still write what we have
_START = time.monotonic()
# Optional per-repo harness config (reasoning-model repos ship one to turn on CoT).
CFG = {}
if os.path.exists("harness_cfg.json"):
try:
CFG = json.load(open("harness_cfg.json"))
except Exception:
CFG = {}
COT = bool(CFG.get("cot", False))
MAX_CAP = int(CFG.get("max_new_cap", 1024))
def elapsed():
return time.monotonic() - _START
def load_model():
tok = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID,
torch_dtype=torch.float16, # T4 has no bfloat16
device_map="auto",
trust_remote_code=True,
).eval()
if tok.pad_token_id is None:
tok.pad_token = tok.eos_token
return tok, model
def generate(tok, model, messages, max_new_tokens):
inputs = tok.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
).to(model.device)
with torch.no_grad():
out = model.generate(
inputs,
max_new_tokens=max_new_tokens,
do_sample=False, # greedy => reproducible
num_beams=1,
pad_token_id=tok.pad_token_id,
)
return tok.decode(out[0][inputs.shape[-1] :], skip_special_tokens=True).strip()
def main():
df = pd.read_csv(TEST_CSV, dtype=str).fillna("")
total = len(df)
print(f"loaded {total} problems from {TEST_CSV}", flush=True)
tok, model = load_model()
print(f"model loaded at {elapsed():.0f}s", flush=True)
records = []
for i, row in df.iterrows():
rid = row["id"]
context = row.get("context", "")
query = row.get("query", "")
task_type = row.get("task_type", "")
n = H.count_items(context, query, task_type)
preds = [""] * n # safe default so every item has a slot
if elapsed() < SAFETY_S:
try:
messages = H.build_messages(context, query, task_type, n, cot=COT)
budget = H.max_new_tokens_for(task_type, n, cot=COT, cap=MAX_CAP)
text = generate(tok, model, messages, budget)
preds = H.parse_answers(text, n)
except Exception as exc: # never let one row sink the whole run
print(f"[warn] id={rid} failed: {exc!r}", flush=True)
else:
print(f"[warn] time budget hit; blanking id={rid}", flush=True)
records.append({"id": rid, "pred": json.dumps(preds, ensure_ascii=False)})
if (i + 1) % 5 == 0 or (i + 1) == total:
print(f"{i + 1}/{total} done ({elapsed():.0f}s)", flush=True)
pd.DataFrame(records, columns=["id", "pred"]).to_csv(OUT_CSV, index=False)
print(f"wrote {OUT_CSV} ({len(records)} rows) at {elapsed():.0f}s", flush=True)
if __name__ == "__main__":
main()

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<｜begin▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:749a967cd78e972e9b7f20adaa0a14459c4f738b69cff9d600d9556f9b6b53f6
size 5212541

195
tokenizer_config.json Normal file
View File

@@ -0,0 +1,195 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"151643": {
"content": "<｜end▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<｜User｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151645": {
"content": "<｜Assistant｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151646": {
"content": "<｜begin▁of▁sentence｜>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|EOT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151648": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151649": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<｜begin▁of▁sentence｜>",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<｜end▁of▁sentence｜>",
"extra_special_tokens": {},
"legacy": true,
"model_max_length": 16384,
"pad_token": "<｜end▁of▁sentence｜>",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": null,
"use_default_system_prompt": false
}