DEMOThis report is public and visible to anyone with the link for 30 days, then deleted. Save privately — create free account
phi-4-mini-instruct.Q4_K_M.gguf
Format: GGUF  ·  Size: 2376.4 MB  ·  Scanned: 2026-10-07  ·  83567 ms
SHA256: 88c00229914083cd112853aab84ed51b87bdf6b9…

Security grade

B
Score: 83/100
1 MEDIUM 3 LOW 3 INFO
Artifact Security
B / 83
Repository Trust
N/A
local upload
Deployment Confidence
Medium
Artifact Security grades the file. Repository Trust is unavailable for local uploads — no external provenance to verify. Deployment Confidence reflects artifact grade only.
▶ Score breakdown
Base score 100
MEDIUM External URLs embedded in 1 KV metadata field(s) -8
LOW No license field in GGUF metadata (general.license) -3
LOW No embedded provenance metadata -3
LOW Fine-tuned model without traceable base_model field -3
Penalty subtotal 83/100
Final B / 83
GGUF v3 model | architecture: phi3 | size: mini | quantization: Q4_K | 196 tensors | 4 warnings / 3 informational

Runtime compatibility

Runtime Status Quant Architecture Context
llama.cpp ✓ ✓ ✓ 128k — may require flash attention (--flash-attn) and large VRAM
Ollama ✓ ✓ ✓ 128k — may require flash attention (--flash-attn) and large VRAM
LM Studio ✓ ✓ ✓ 128k — may require flash attention (--flash-attn) and large VRAM
vLLM ✗ N/A GGUF not supported — requires safetensors format
HuggingFace Transformers ✗ N/A GGUF not directly supported — use safetensors or PyTorch checkpoint

Model info

Architecture
Neural network family — determines which runtime can load this model
phi3
NamePhi 4 Mini Instruct
Size label
Human-readable parameter count from model metadata
mini
Quantization
Weight storage format derived from actual tensor dtypes; lower bits = smaller file and faster inference at the cost of accuracy
 Q4_K
Parameters ~
Estimated total number of weight values; determines VRAM needed at inference
3,836,021,856
Context length
Maximum tokens the model can process in a single prompt+response; affects KV-cache memory
131,072 tokens
Embedding dim
Hidden state dimension (d_model); larger = more expressive but more compute per token
3,072
FFN dim
Feed-forward network intermediate size; typically 2.7–4× embedding_length
8,192
Layers
Number of transformer blocks (depth); more layers = more reasoning capacity
32
Attention heads (Q)
Number of query heads; GQA/MQA models use fewer KV heads than Q heads
24
KV heads
Key/Value heads per layer; fewer than Q heads = GQA; list = per-layer (hybrid architecture)
 8 (GQA: 24 Q → 8 KV)
Vocab size
Number of unique tokens the tokenizer knows; affects embedding table size
200,064
BOS / EOS tokens
Beginning-of-sequence and end-of-sequence token IDs used by the tokenizer
199999 / 200020
Tokenizer
Tokenizer algorithm family (e.g. gpt2 = BPE, llama = SentencePiece)
gpt2
Chat template
Jinja2 prompt template embedded in model; controls how messages are formatted for inference
✓ Yes — see section below
Fine-tune
Fine-tune descriptor from metadata; indicates this is an adapted version of a base model
instruct
Tensors
Total number of weight tensors stored in the file
196
File size
Size on disk in megabytes
2376.44 MB

Security findings (7)

MEDIUM Metadata Security
External URLs embedded in 1 KV metadata field(s)
Fields: ['general.repo_url']
→ URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch
LOW Supply Chain
No license field in GGUF metadata (general.license)
Absence of license information makes it impossible to determine usage rights
→ Add general.license to model metadata before distributing; use an SPDX identifier
LOW Supply Chain
No embedded provenance metadata
None of general.author, general.source.url, general.base_model.0, or general.source.huggingface.repository are embedded in the GGUF file. Without any origin signal the model cannot be traced to a trusted source or compared against a reference checkpoint for tampering detection. For files uploaded directly, provenance is especially critical because the scanner cannot infer repository origin from the file alone.
→ Add at least one of: general.author, general.source.huggingface.repository, or general.source.url
LOW Supply Chain
Fine-tuned model without traceable base_model field
Fine-tunes should declare the base model via general.base_model.0 for supply-chain transparency
→ Add general.base_model.0 with the HuggingFace repo of the base model
INFO Architecture
Grouped Query Attention (GQA) detected
head_count=24, head_count_kv=8 — requires GQA-aware runtime
→ Ensure your runtime (llama.cpp >= b1500, Ollama >= 0.1.30) supports GQA
INFO Embedding Size
Large embedding tensor 'token_embd.weight': 504,161,280 bytes
vocab=200,064 x emb_dim=3,072 x 0.8203125 B/elem -> expected 504,161,280 B — size is consistent with architecture
→ No action needed; large embeddings are expected for large-vocabulary models
INFO Quantization
Model is quantized: Q4_K, Q5_K, Q6_K
Quantization reduces size and inference cost at the expense of some accuracy
→ Verify the quantization level is appropriate for your use case (Q4_K_M is a common balanced choice)

Integrity & Structure

SHA-25688c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a
SHA-512f6439161dcca987a66342352ef177e8b45db26b61575ff819e25ef2b6d765d0b8edcd04c6c4fb073…
File size (bytes)2,491,874,272
Header + KV + tensor directory8,250,976 bytes (7.87 MB)
Tensor data region2,483,623,296 bytes (2368.57 MB)
Trailing bytes0
Unaccounted bytes0 ✓
KV metadata keys35
Tensors parsed196
Offsets monotone✓ OK
Max tensor offset2,455,311,744

DType Mix

DTypeCountTotal bytesTotal MBAvg bits/elem
Q4_K 80 1,302,331,392 1242.0 4.5
Q6_K 17 834,462,720 795.81 6.5625
Q5_K 32 346,030,080 330.0 5.5
F32 67 799,104 0.76 32.0

Chat Template

tokenizer.chat_template (398 chars) — click to collapse 
{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}

This is a prompt template (non-executable). If your application implements tool-calling agents, enforce a whitelist + schema validation for any <tool_call> output.

Tensor Preview (first 50 of 196)

#NameDimsDTypeOffsetBytesbits/elem
0 output_norm.weight [3072] F32 0 12,288 32.0
1 rope_factors_long.weight [48] F32 12,288 192 32.0
2 rope_factors_short.weight [48] F32 12,480 192 32.0
3 token_embd.weight [3072, 200064] Q6_K 12,672 504,161,280 6.5625
4 blk.0.attn_norm.weight [3072] F32 504,173,952 12,288 32.0
5 blk.0.attn_output.weight [3072, 3072] Q4_K 504,186,240 5,308,416 4.5
6 blk.0.attn_qkv.weight [3072, 5120] Q5_K 509,494,656 10,813,440 5.5
7 blk.0.ffn_down.weight [8192, 3072] Q6_K 520,308,096 20,643,840 6.5625
8 blk.0.ffn_norm.weight [3072] F32 540,951,936 12,288 32.0
9 blk.0.ffn_up.weight [3072, 16384] Q4_K 540,964,224 28,311,552 4.5
10 blk.1.attn_norm.weight [3072] F32 569,275,776 12,288 32.0
11 blk.1.attn_output.weight [3072, 3072] Q4_K 569,288,064 5,308,416 4.5
12 blk.1.attn_qkv.weight [3072, 5120] Q5_K 574,596,480 10,813,440 5.5
13 blk.1.ffn_down.weight [8192, 3072] Q6_K 585,409,920 20,643,840 6.5625
14 blk.1.ffn_norm.weight [3072] F32 606,053,760 12,288 32.0
15 blk.1.ffn_up.weight [3072, 16384] Q4_K 606,066,048 28,311,552 4.5
16 blk.2.attn_norm.weight [3072] F32 634,377,600 12,288 32.0
17 blk.2.attn_output.weight [3072, 3072] Q4_K 634,389,888 5,308,416 4.5
18 blk.2.attn_qkv.weight [3072, 5120] Q5_K 639,698,304 10,813,440 5.5
19 blk.2.ffn_down.weight [8192, 3072] Q6_K 650,511,744 20,643,840 6.5625
20 blk.2.ffn_norm.weight [3072] F32 671,155,584 12,288 32.0
21 blk.2.ffn_up.weight [3072, 16384] Q4_K 671,167,872 28,311,552 4.5
22 blk.3.attn_norm.weight [3072] F32 699,479,424 12,288 32.0
23 blk.3.attn_output.weight [3072, 3072] Q4_K 699,491,712 5,308,416 4.5
24 blk.3.attn_qkv.weight [3072, 5120] Q5_K 704,800,128 10,813,440 5.5
25 blk.3.ffn_down.weight [8192, 3072] Q6_K 715,613,568 20,643,840 6.5625
26 blk.3.ffn_norm.weight [3072] F32 736,257,408 12,288 32.0
27 blk.3.ffn_up.weight [3072, 16384] Q4_K 736,269,696 28,311,552 4.5
28 blk.4.attn_norm.weight [3072] F32 764,581,248 12,288 32.0
29 blk.4.attn_output.weight [3072, 3072] Q4_K 764,593,536 5,308,416 4.5
30 blk.4.attn_qkv.weight [3072, 5120] Q5_K 769,901,952 10,813,440 5.5
31 blk.4.ffn_down.weight [8192, 3072] Q4_K 780,715,392 14,155,776 4.5
32 blk.4.ffn_norm.weight [3072] F32 794,871,168 12,288 32.0
33 blk.4.ffn_up.weight [3072, 16384] Q4_K 794,883,456 28,311,552 4.5
34 blk.5.attn_norm.weight [3072] F32 823,195,008 12,288 32.0
35 blk.5.attn_output.weight [3072, 3072] Q4_K 823,207,296 5,308,416 4.5
36 blk.5.attn_qkv.weight [3072, 5120] Q5_K 828,515,712 10,813,440 5.5
37 blk.5.ffn_down.weight [8192, 3072] Q4_K 839,329,152 14,155,776 4.5
38 blk.5.ffn_norm.weight [3072] F32 853,484,928 12,288 32.0
39 blk.5.ffn_up.weight [3072, 16384] Q4_K 853,497,216 28,311,552 4.5
40 blk.6.attn_norm.weight [3072] F32 881,808,768 12,288 32.0
41 blk.6.attn_output.weight [3072, 3072] Q4_K 881,821,056 5,308,416 4.5
42 blk.6.attn_qkv.weight [3072, 5120] Q5_K 887,129,472 10,813,440 5.5
43 blk.6.ffn_down.weight [8192, 3072] Q6_K 897,942,912 20,643,840 6.5625
44 blk.6.ffn_norm.weight [3072] F32 918,586,752 12,288 32.0
45 blk.6.ffn_up.weight [3072, 16384] Q4_K 918,599,040 28,311,552 4.5
46 blk.7.attn_norm.weight [3072] F32 946,910,592 12,288 32.0
47 blk.7.attn_output.weight [3072, 3072] Q4_K 946,922,880 5,308,416 4.5
48 blk.7.attn_qkv.weight [3072, 5120] Q5_K 952,231,296 10,813,440 5.5
49 blk.7.ffn_down.weight [8192, 3072] Q4_K 963,044,736 14,155,776 4.5
… 146 more tensors omitted from preview

Scan coverage

Checks performed
  • ✓Magic bytes &amp; GGUF version validation
  • ✓Header parse (tensor count, KV count)
  • ✓KV metadata parse — all key/value pairs
  • ✓Tensor directory parse (names, dims, dtype, offsets)
  • ✓Tensor offset monotonicity
  • ✓Tensor overlap detection
  • ✓Tensor out-of-bounds detection
  • ✓Data section alignment verification
  • ✓Trailing bytes after last tensor
  • ✓Unaccounted bytes (header vs file size)
  • ✓Dtype histogram &amp; quantization mix analysis
  • ✓Embedding tensor size cross-validation
  • ✓Chat template static scan (Jinja2/SSTI patterns)
  • ✓Runtime compatibility heuristics
  • —External model card / repository context: not available for local upload
  • —Upstream repository: not checked — not available for direct file upload
Not covered
  • ✗Runtime execution or dynamic analysis
  • ✗Behavioral backdoor detection
  • ✗Weight-level semantic backdoor detection
  • ✗Full upstream repository verification
  • ✗License validation beyond embedded metadata
  • ✗Malware scanning of surrounding repo files
  • ✗Adversarial robustness or alignment audit
  • ✗Training data provenance
ⓘ Static scanning can detect structural anomalies and known malicious patterns. It cannot guarantee absence of risk. Treat results as a security signal, not a formal audit.
Raw scan data (.llmscan JSON) 
{
  "compatibility": [
    {
      "arch": true,
      "container": true,
      "context": "128k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF v3 container: supported | quant Q4_K: supported | 128k context: requires sufficient VRAM/RAM and --ctx-size flag",
      "quant": true,
      "runtime": "llama.cpp",
      "supported": true
    },
    {
      "arch": true,
      "container": true,
      "context": "128k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF via llama.cpp backend: container and quantization supported",
      "quant": true,
      "runtime": "Ollama",
      "supported": true
    },
    {
      "arch": true,
      "container": true,
      "context": "128k \u2014 may require flash attention (--flash-attn) and large VRAM",
      "notes": "GGUF container and quantization supported; GPU/CPU inference",
      "quant": true,
      "runtime": "LM Studio",
      "supported": true
    },
    {
      "arch": null,
      "container": false,
      "context": null,
      "not_supported_msg": "GGUF not supported \u2014 requires safetensors format",
      "notes": "GGUF not supported; requires safetensors format",
      "quant": false,
      "runtime": "vLLM",
      "supported": false
    },
    {
      "arch": null,
      "container": false,
      "context": null,
      "not_supported_msg": "GGUF not directly supported \u2014 use safetensors or PyTorch checkpoint",
      "notes": "GGUF not supported; requires safetensors or PyTorch checkpoint",
      "quant": false,
      "runtime": "HuggingFace Transformers",
      "supported": false
    }
  ],
  "format": "LLM-SCAN",
  "format_version": "1.0",
  "generator": {
    "name": "llmscan-engine",
    "version": "2.0.0"
  },
  "model": {
    "alignment": 32,
    "arch": "phi3",
    "architecture": "phi3",
    "basename": "Phi-4",
    "block_count": 32,
    "bos_token_id": 199999,
    "chat_template": "{% for message in messages %}{% if message[\u0027role\u0027] == \u0027system\u0027 and \u0027tools\u0027 in message and message[\u0027tools\u0027] is not none %}{{ \u0027\u003c|\u0027 + message[\u0027role\u0027] + \u0027|\u003e\u0027 + message[\u0027content\u0027] + \u0027\u003c|tool|\u003e\u0027 + message[\u0027tools\u0027] + \u0027\u003c|/tool|\u003e\u0027 + \u0027\u003c|end|\u003e\u0027 }}{% else %}{{ \u0027\u003c|\u0027 + message[\u0027role\u0027] + \u0027|\u003e\u0027 + message[\u0027content\u0027] + \u0027\u003c|end|\u003e\u0027 }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ \u0027\u003c|assistant|\u003e\u0027 }}{% endif %}",
    "context_length": 131072,
    "dtype_histogram": {
      "F32": 67,
      "Q4_K": 80,
      "Q5_K": 32,
      "Q6_K": 17
    },
    "dtype_percentage": {
      "F32": 34.2,
      "Q4_K": 40.8,
      "Q5_K": 16.3,
      "Q6_K": 8.7
    },
    "dtype_stats": {
      "F32": {
        "avg_bits_per_elem": 32.0,
        "bytes": 799104,
        "count": 67,
        "mb": 0.76
      },
      "Q4_K": {
        "avg_bits_per_elem": 4.5,
        "bytes": 1302331392,
        "count": 80,
        "mb": 1242.0
      },
      "Q5_K": {
        "avg_bits_per_elem": 5.5,
        "bytes": 346030080,
        "count": 32,
        "mb": 330.0
      },
      "Q6_K": {
        "avg_bits_per_elem": 6.5625,
        "bytes": 834462720,
        "count": 17,
        "mb": 795.81
      }
    },
    "embedding_length": 3072,
    "eos_token_id": 200020,
    "feed_forward_length": 8192,
    "file_size_bytes": 2491874272,
    "file_size_mb": 2376.44,
    "finetune": "instruct",
    "format": "gguf",
    "gguf_version": 3,
    "has_chat_template": true,
    "head_count": 24,
    "head_count_kv": 8,
    "header_kv_dir_bytes": 8250976,
    "kv_count": 35,
    "kv_meta": {
      "keys": [
        "general.architecture",
        "general.basename",
        "general.file_type",
        "general.finetune",
        "general.name",
        "general.organization",
        "general.quantization_version",
        "general.quantized_by",
        "general.repo_url",
        "general.size_label",
        "general.type",
        "phi3.attention.head_count",
        "phi3.attention.head_count_kv",
        "phi3.attention.layer_norm_rms_epsilon",
        "phi3.attention.sliding_window",
        "phi3.block_count",
        "phi3.context_length",
        "phi3.embedding_length",
        "phi3.feed_forward_length",
        "phi3.rope.dimension_count",
        "phi3.rope.freq_base",
        "phi3.rope.scaling.attn_factor",
        "phi3.rope.scaling.original_context_length",
        "tokenizer.chat_template",
        "tokenizer.ggml.add_bos_token",
        "tokenizer.ggml.add_eos_token",
        "tokenizer.ggml.bos_token_id",
        "tokenizer.ggml.eos_token_id",
        "tokenizer.ggml.merges",
        "tokenizer.ggml.model",
        "tokenizer.ggml.padding_token_id",
        "tokenizer.ggml.pre",
        "tokenizer.ggml.token_type",
        "tokenizer.ggml.tokens",
        "tokenizer.ggml.unknown_token_id"
      ],
      "kv_count": 35,
      "values_redacted": true
    },
    "license": null,
    "max_tensor_offset": 2455311744,
    "misaligned_tensors": 0,
    "model_name": "Phi 4 Mini Instruct",
    "offsets_monotone": true,
    "oob_tensor_count": 0,
    "overlapping_tensor_pairs": 0,
    "param_estimate": 3836021856,
    "params_estimate": 3836021856,
    "quantization": "Q4_K",
    "scanner_model_info": {
      "alignment": 32,
      "architecture": "phi3",
      "basename": "Phi-4",
      "block_count": 32,
      "bos_token_id": 199999,
      "chat_template": "{% for message in messages %}{% if message[\u0027role\u0027] == \u0027system\u0027 and \u0027tools\u0027 in message and message[\u0027tools\u0027] is not none %}{{ \u0027\u003c|\u0027 + message[\u0027role\u0027] + \u0027|\u003e\u0027 + message[\u0027content\u0027] + \u0027\u003c|tool|\u003e\u0027 + message[\u0027tools\u0027] + \u0027\u003c|/tool|\u003e\u0027 + \u0027\u003c|end|\u003e\u0027 }}{% else %}{{ \u0027\u003c|\u0027 + message[\u0027role\u0027] + \u0027|\u003e\u0027 + message[\u0027content\u0027] + \u0027\u003c|end|\u003e\u0027 }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ \u0027\u003c|assistant|\u003e\u0027 }}{% endif %}",
      "context_length": 131072,
      "data_section_start": 8250976,
      "dtype_histogram": {
        "F32": 67,
        "Q4_K": 80,
        "Q5_K": 32,
        "Q6_K": 17
      },
      "dtype_percentage": {
        "F32": 34.2,
        "Q4_K": 40.8,
        "Q5_K": 16.3,
        "Q6_K": 8.7
      },
      "dtype_stats": {
        "F32": {
          "avg_bits_per_elem": 32.0,
          "bytes": 799104,
          "count": 67,
          "mb": 0.76
        },
        "Q4_K": {
          "avg_bits_per_elem": 4.5,
          "bytes": 1302331392,
          "count": 80,
          "mb": 1242.0
        },
        "Q5_K": {
          "avg_bits_per_elem": 5.5,
          "bytes": 346030080,
          "count": 32,
          "mb": 330.0
        },
        "Q6_K": {
          "avg_bits_per_elem": 6.5625,
          "bytes": 834462720,
          "count": 17,
          "mb": 795.81
        }
      },
      "embedding_length": 3072,
      "eos_token_id": 200020,
      "feed_forward_length": 8192,
      "file_size_bytes": 2491874272,
      "file_size_mb": 2376.44,
      "finetune": "instruct",
      "has_chat_template": true,
      "head_count": 24,
      "head_count_kv": 8,
      "header_end_offset": 8250946,
      "header_kv_dir_bytes": 8250976,
      "kv_count": 35,
      "kv_keys": [
        "general.architecture",
        "general.basename",
        "general.file_type",
        "general.finetune",
        "general.name",
        "general.organization",
        "general.quantization_version",
        "general.quantized_by",
        "general.repo_url",
        "general.size_label",
        "general.type",
        "phi3.attention.head_count",
        "phi3.attention.head_count_kv",
        "phi3.attention.layer_norm_rms_epsilon",
        "phi3.attention.sliding_window",
        "phi3.block_count",
        "phi3.context_length",
        "phi3.embedding_length",
        "phi3.feed_forward_length",
        "phi3.rope.dimension_count",
        "phi3.rope.freq_base",
        "phi3.rope.scaling.attn_factor",
        "phi3.rope.scaling.original_context_length",
        "tokenizer.chat_template",
        "tokenizer.ggml.add_bos_token",
        "tokenizer.ggml.add_eos_token",
        "tokenizer.ggml.bos_token_id",
        "tokenizer.ggml.eos_token_id",
        "tokenizer.ggml.merges",
        "tokenizer.ggml.model",
        "tokenizer.ggml.padding_token_id",
        "tokenizer.ggml.pre",
        "tokenizer.ggml.token_type",
        "tokenizer.ggml.tokens",
        "tokenizer.ggml.unknown_token_id"
      ],
      "license": null,
      "magic": "GGUF",
      "max_tensor_offset": 2455311744,
      "misaligned_tensors": 0,
      "model_name": "Phi 4 Mini Instruct",
      "offsets_monotone": true,
      "oob_tensor_count": 0,
      "overlapping_tensor_pairs": 0,
      "param_estimate": 3836021856,
      "quantization": "Q4_K",
      "sha256": "88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a",
      "sha512": "f6439161dcca987a66342352ef177e8b45db26b61575ff819e25ef2b6d765d0b8edcd04c6c4fb0739fdd1be0e01004f21958bfeca09c518c6fadaa7d8a12335f",
      "size_label": "mini",
      "tensor_bytes_sum": 2483623296,
      "tensor_count": 196,
      "tensor_delta_bytes": 8250976,
      "tensor_delta_mb": 7.87,
      "tensor_preview": [
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 0,
          "name": "output_norm.weight",
          "offset": 0
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 192,
          "dims": [
            48
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 1,
          "name": "rope_factors_long.weight",
          "offset": 12288
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 192,
          "dims": [
            48
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 2,
          "name": "rope_factors_short.weight",
          "offset": 12480
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 504161280,
          "dims": [
            3072,
            200064
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 3,
          "name": "token_embd.weight",
          "offset": 12672
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 4,
          "name": "blk.0.attn_norm.weight",
          "offset": 504173952
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 5,
          "name": "blk.0.attn_output.weight",
          "offset": 504186240
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 6,
          "name": "blk.0.attn_qkv.weight",
          "offset": 509494656
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 20643840,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 7,
          "name": "blk.0.ffn_down.weight",
          "offset": 520308096
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 8,
          "name": "blk.0.ffn_norm.weight",
          "offset": 540951936
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 9,
          "name": "blk.0.ffn_up.weight",
          "offset": 540964224
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 10,
          "name": "blk.1.attn_norm.weight",
          "offset": 569275776
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 11,
          "name": "blk.1.attn_output.weight",
          "offset": 569288064
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 12,
          "name": "blk.1.attn_qkv.weight",
          "offset": 574596480
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 20643840,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 13,
          "name": "blk.1.ffn_down.weight",
          "offset": 585409920
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 14,
          "name": "blk.1.ffn_norm.weight",
          "offset": 606053760
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 15,
          "name": "blk.1.ffn_up.weight",
          "offset": 606066048
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 16,
          "name": "blk.2.attn_norm.weight",
          "offset": 634377600
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 17,
          "name": "blk.2.attn_output.weight",
          "offset": 634389888
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 18,
          "name": "blk.2.attn_qkv.weight",
          "offset": 639698304
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 20643840,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 19,
          "name": "blk.2.ffn_down.weight",
          "offset": 650511744
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 20,
          "name": "blk.2.ffn_norm.weight",
          "offset": 671155584
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 21,
          "name": "blk.2.ffn_up.weight",
          "offset": 671167872
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 22,
          "name": "blk.3.attn_norm.weight",
          "offset": 699479424
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 23,
          "name": "blk.3.attn_output.weight",
          "offset": 699491712
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 24,
          "name": "blk.3.attn_qkv.weight",
          "offset": 704800128
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 20643840,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 25,
          "name": "blk.3.ffn_down.weight",
          "offset": 715613568
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 26,
          "name": "blk.3.ffn_norm.weight",
          "offset": 736257408
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 27,
          "name": "blk.3.ffn_up.weight",
          "offset": 736269696
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 28,
          "name": "blk.4.attn_norm.weight",
          "offset": 764581248
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 29,
          "name": "blk.4.attn_output.weight",
          "offset": 764593536
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 30,
          "name": "blk.4.attn_qkv.weight",
          "offset": 769901952
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 14155776,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 31,
          "name": "blk.4.ffn_down.weight",
          "offset": 780715392
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 32,
          "name": "blk.4.ffn_norm.weight",
          "offset": 794871168
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 33,
          "name": "blk.4.ffn_up.weight",
          "offset": 794883456
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 34,
          "name": "blk.5.attn_norm.weight",
          "offset": 823195008
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 35,
          "name": "blk.5.attn_output.weight",
          "offset": 823207296
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 36,
          "name": "blk.5.attn_qkv.weight",
          "offset": 828515712
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 14155776,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 37,
          "name": "blk.5.ffn_down.weight",
          "offset": 839329152
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 38,
          "name": "blk.5.ffn_norm.weight",
          "offset": 853484928
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 39,
          "name": "blk.5.ffn_up.weight",
          "offset": 853497216
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 40,
          "name": "blk.6.attn_norm.weight",
          "offset": 881808768
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 41,
          "name": "blk.6.attn_output.weight",
          "offset": 881821056
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 42,
          "name": "blk.6.attn_qkv.weight",
          "offset": 887129472
        },
        {
          "bits_per_elem": 6.5625,
          "byte_len": 20643840,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 14,
          "dtype_name": "Q6_K",
          "index": 43,
          "name": "blk.6.ffn_down.weight",
          "offset": 897942912
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 44,
          "name": "blk.6.ffn_norm.weight",
          "offset": 918586752
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 45,
          "name": "blk.6.ffn_up.weight",
          "offset": 918599040
        },
        {
          "bits_per_elem": 32.0,
          "byte_len": 12288,
          "dims": [
            3072
          ],
          "dtype_id": 0,
          "dtype_name": "F32",
          "index": 46,
          "name": "blk.7.attn_norm.weight",
          "offset": 946910592
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 5308416,
          "dims": [
            3072,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 47,
          "name": "blk.7.attn_output.weight",
          "offset": 946922880
        },
        {
          "bits_per_elem": 5.5,
          "byte_len": 10813440,
          "dims": [
            3072,
            5120
          ],
          "dtype_id": 13,
          "dtype_name": "Q5_K",
          "index": 48,
          "name": "blk.7.attn_qkv.weight",
          "offset": 952231296
        },
        {
          "bits_per_elem": 4.5,
          "byte_len": 14155776,
          "dims": [
            8192,
            3072
          ],
          "dtype_id": 12,
          "dtype_name": "Q4_K",
          "index": 49,
          "name": "blk.7.ffn_down.weight",
          "offset": 963044736
        }
      ],
      "tokenizer_model": "gpt2",
      "top_tensors_by_size": [
        {
          "byte_len": 504161280,
          "dims": [
            3072,
            200064
          ],
          "dtype": "Q6_K",
          "n_elem": 614596608,
          "name": "token_embd.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.0.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.1.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.2.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.3.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.4.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.5.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.6.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.7.ffn_up.weight"
        },
        {
          "byte_len": 28311552,
          "dims": [
            3072,
            16384
          ],
          "dtype": "Q4_K",
          "n_elem": 50331648,
          "name": "blk.8.ffn_up.weight"
        }
      ],
      "trailing_bytes": 0,
      "unaccounted_bytes": 0,
      "version": 3,
      "vocab_size": 200064
    },
    "sha256": "88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a",
    "sha512": "f6439161dcca987a66342352ef177e8b45db26b61575ff819e25ef2b6d765d0b8edcd04c6c4fb0739fdd1be0e01004f21958bfeca09c518c6fadaa7d8a12335f",
    "size_label": "mini",
    "tensor_bytes_sum": 2483623296,
    "tensor_count": 196,
    "tensor_delta_bytes": 8250976,
    "tensor_delta_mb": 7.87,
    "tensor_preview": [
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 0,
        "name": "output_norm.weight",
        "offset": 0
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 192,
        "dims": [
          48
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 1,
        "name": "rope_factors_long.weight",
        "offset": 12288
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 192,
        "dims": [
          48
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 2,
        "name": "rope_factors_short.weight",
        "offset": 12480
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 504161280,
        "dims": [
          3072,
          200064
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 3,
        "name": "token_embd.weight",
        "offset": 12672
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 4,
        "name": "blk.0.attn_norm.weight",
        "offset": 504173952
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 5,
        "name": "blk.0.attn_output.weight",
        "offset": 504186240
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 6,
        "name": "blk.0.attn_qkv.weight",
        "offset": 509494656
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 7,
        "name": "blk.0.ffn_down.weight",
        "offset": 520308096
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 8,
        "name": "blk.0.ffn_norm.weight",
        "offset": 540951936
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 9,
        "name": "blk.0.ffn_up.weight",
        "offset": 540964224
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 10,
        "name": "blk.1.attn_norm.weight",
        "offset": 569275776
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 11,
        "name": "blk.1.attn_output.weight",
        "offset": 569288064
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 12,
        "name": "blk.1.attn_qkv.weight",
        "offset": 574596480
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 13,
        "name": "blk.1.ffn_down.weight",
        "offset": 585409920
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 14,
        "name": "blk.1.ffn_norm.weight",
        "offset": 606053760
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 15,
        "name": "blk.1.ffn_up.weight",
        "offset": 606066048
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 16,
        "name": "blk.2.attn_norm.weight",
        "offset": 634377600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 17,
        "name": "blk.2.attn_output.weight",
        "offset": 634389888
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 18,
        "name": "blk.2.attn_qkv.weight",
        "offset": 639698304
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 19,
        "name": "blk.2.ffn_down.weight",
        "offset": 650511744
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 20,
        "name": "blk.2.ffn_norm.weight",
        "offset": 671155584
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 21,
        "name": "blk.2.ffn_up.weight",
        "offset": 671167872
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 22,
        "name": "blk.3.attn_norm.weight",
        "offset": 699479424
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 23,
        "name": "blk.3.attn_output.weight",
        "offset": 699491712
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 24,
        "name": "blk.3.attn_qkv.weight",
        "offset": 704800128
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 25,
        "name": "blk.3.ffn_down.weight",
        "offset": 715613568
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 26,
        "name": "blk.3.ffn_norm.weight",
        "offset": 736257408
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 27,
        "name": "blk.3.ffn_up.weight",
        "offset": 736269696
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 28,
        "name": "blk.4.attn_norm.weight",
        "offset": 764581248
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 29,
        "name": "blk.4.attn_output.weight",
        "offset": 764593536
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 30,
        "name": "blk.4.attn_qkv.weight",
        "offset": 769901952
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 31,
        "name": "blk.4.ffn_down.weight",
        "offset": 780715392
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 32,
        "name": "blk.4.ffn_norm.weight",
        "offset": 794871168
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 33,
        "name": "blk.4.ffn_up.weight",
        "offset": 794883456
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 34,
        "name": "blk.5.attn_norm.weight",
        "offset": 823195008
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 35,
        "name": "blk.5.attn_output.weight",
        "offset": 823207296
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 36,
        "name": "blk.5.attn_qkv.weight",
        "offset": 828515712
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 37,
        "name": "blk.5.ffn_down.weight",
        "offset": 839329152
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 38,
        "name": "blk.5.ffn_norm.weight",
        "offset": 853484928
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 39,
        "name": "blk.5.ffn_up.weight",
        "offset": 853497216
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 40,
        "name": "blk.6.attn_norm.weight",
        "offset": 881808768
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 41,
        "name": "blk.6.attn_output.weight",
        "offset": 881821056
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 42,
        "name": "blk.6.attn_qkv.weight",
        "offset": 887129472
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 43,
        "name": "blk.6.ffn_down.weight",
        "offset": 897942912
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 44,
        "name": "blk.6.ffn_norm.weight",
        "offset": 918586752
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 45,
        "name": "blk.6.ffn_up.weight",
        "offset": 918599040
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 46,
        "name": "blk.7.attn_norm.weight",
        "offset": 946910592
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 47,
        "name": "blk.7.attn_output.weight",
        "offset": 946922880
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 48,
        "name": "blk.7.attn_qkv.weight",
        "offset": 952231296
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 49,
        "name": "blk.7.ffn_down.weight",
        "offset": 963044736
      }
    ],
    "tokenizer_model": "gpt2",
    "top_tensors_by_size": [
      {
        "byte_len": 504161280,
        "dims": [
          3072,
          200064
        ],
        "dtype": "Q6_K",
        "n_elem": 614596608,
        "name": "token_embd.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.0.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.1.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.2.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.3.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.4.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.5.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.6.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.7.ffn_up.weight"
      },
      {
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype": "Q4_K",
        "n_elem": 50331648,
        "name": "blk.8.ffn_up.weight"
      }
    ],
    "trailing_bytes": 0,
    "unaccounted_bytes": 0,
    "values_redacted": true,
    "vocab_size": 200064
  },
  "report": {
    "bullets": [
      "GGUF v3 model | architecture: phi3 | size: mini | quantization: Q4_K | 196 tensors | 4 warnings / 3 informational",
      "Size: 2376.44 MB",
      "SHA256: 88c00229914083cd..."
    ],
    "recommendations": [
      "URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch",
      "Add general.license to model metadata before distributing; use an SPDX identifier",
      "Add at least one of: general.author, general.source.huggingface.repository, or general.source.url",
      "Add general.base_model.0 with the HuggingFace repo of the base model"
    ],
    "summary": "GGUF v3 model | architecture: phi3 | size: mini | quantization: Q4_K | 196 tensors | 4 warnings / 3 informational"
  },
  "scan_context": {
    "duration_ms": 83567,
    "ended_at": "2026-10-07T08:42:45+00:00Z",
    "limits": {
      "sandbox": true,
      "timeout_ms": 60000
    },
    "mode": "static-deep",
    "started_at": "2026-10-07T08:42:45+00:00Z"
  },
  "security": {
    "findings": [
      {
        "category": "Architecture",
        "detail": "head_count=24, head_count_kv=8 \u2014 requires GQA-aware runtime",
        "recommendation": "Ensure your runtime (llama.cpp \u003e= b1500, Ollama \u003e= 0.1.30) supports GQA",
        "severity": "INFO",
        "title": "Grouped Query Attention (GQA) detected"
      },
      {
        "category": "Metadata Security",
        "detail": "Fields: [\u0027general.repo_url\u0027]",
        "recommendation": "URLs in model metadata may be used for tracking or exfiltration when metadata is rendered; do not auto-fetch",
        "severity": "MEDIUM",
        "title": "External URLs embedded in 1 KV metadata field(s)"
      },
      {
        "category": "Supply Chain",
        "detail": "Absence of license information makes it impossible to determine usage rights",
        "recommendation": "Add general.license to model metadata before distributing; use an SPDX identifier",
        "severity": "LOW",
        "title": "No license field in GGUF metadata (general.license)"
      },
      {
        "category": "Supply Chain",
        "detail": "None of general.author, general.source.url, general.base_model.0, or general.source.huggingface.repository are embedded in the GGUF file. Without any origin signal the model cannot be traced to a trusted source or compared against a reference checkpoint for tampering detection. For files uploaded directly, provenance is especially critical because the scanner cannot infer repository origin from the file alone.",
        "recommendation": "Add at least one of: general.author, general.source.huggingface.repository, or general.source.url",
        "severity": "LOW",
        "title": "No embedded provenance metadata"
      },
      {
        "category": "Supply Chain",
        "detail": "Fine-tunes should declare the base model via general.base_model.0 for supply-chain transparency",
        "recommendation": "Add general.base_model.0 with the HuggingFace repo of the base model",
        "severity": "LOW",
        "title": "Fine-tuned model without traceable base_model field"
      },
      {
        "category": "Embedding Size",
        "detail": "vocab=200,064 x emb_dim=3,072 x 0.8203125 B/elem -\u003e expected 504,161,280 B \u2014 size is consistent with architecture",
        "recommendation": "No action needed; large embeddings are expected for large-vocabulary models",
        "severity": "INFO",
        "title": "Large embedding tensor \u0027token_embd.weight\u0027: 504,161,280 bytes"
      },
      {
        "category": "Quantization",
        "detail": "Quantization reduces size and inference cost at the expense of some accuracy",
        "recommendation": "Verify the quantization level is appropriate for your use case (Q4_K_M is a common balanced choice)",
        "severity": "INFO",
        "title": "Model is quantized: Q4_K, Q5_K, Q6_K"
      }
    ],
    "grade": "B",
    "score": 83
  },
  "source": {
    "filename": "phi-4-mini-instruct.Q4_K_M.gguf",
    "hashes": {
      "sha256": "88c00229914083cd112853aab84ed51b87bdf6b9ce42f532d8c85c7c63b1730a"
    },
    "input_type": "file",
    "size_bytes": 2491874272
  },
  "tensors": {
    "count": 196,
    "dtype_histogram": {
      "F32": 67,
      "Q4_K": 80,
      "Q5_K": 32,
      "Q6_K": 17
    },
    "dtype_stats": {
      "F32": {
        "avg_bits_per_elem": 32.0,
        "bytes": 799104,
        "count": 67,
        "mb": 0.76
      },
      "Q4_K": {
        "avg_bits_per_elem": 4.5,
        "bytes": 1302331392,
        "count": 80,
        "mb": 1242.0
      },
      "Q5_K": {
        "avg_bits_per_elem": 5.5,
        "bytes": 346030080,
        "count": 32,
        "mb": 330.0
      },
      "Q6_K": {
        "avg_bits_per_elem": 6.5625,
        "bytes": 834462720,
        "count": 17,
        "mb": 795.81
      }
    },
    "integrity": {
      "header_kv_dir_bytes": 8250976,
      "misaligned_tensors": 0,
      "offsets_monotone": true,
      "oob_tensor_count": 0,
      "overlapping_tensor_pairs": 0,
      "tensor_bytes_sum": 2483623296,
      "tensor_delta_bytes": 8250976,
      "tensor_delta_mb": 7.87,
      "trailing_bytes": 0,
      "unaccounted_bytes": 0
    },
    "preview": [
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 0,
        "name": "output_norm.weight",
        "offset": 0
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 192,
        "dims": [
          48
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 1,
        "name": "rope_factors_long.weight",
        "offset": 12288
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 192,
        "dims": [
          48
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 2,
        "name": "rope_factors_short.weight",
        "offset": 12480
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 504161280,
        "dims": [
          3072,
          200064
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 3,
        "name": "token_embd.weight",
        "offset": 12672
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 4,
        "name": "blk.0.attn_norm.weight",
        "offset": 504173952
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 5,
        "name": "blk.0.attn_output.weight",
        "offset": 504186240
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 6,
        "name": "blk.0.attn_qkv.weight",
        "offset": 509494656
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 7,
        "name": "blk.0.ffn_down.weight",
        "offset": 520308096
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 8,
        "name": "blk.0.ffn_norm.weight",
        "offset": 540951936
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 9,
        "name": "blk.0.ffn_up.weight",
        "offset": 540964224
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 10,
        "name": "blk.1.attn_norm.weight",
        "offset": 569275776
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 11,
        "name": "blk.1.attn_output.weight",
        "offset": 569288064
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 12,
        "name": "blk.1.attn_qkv.weight",
        "offset": 574596480
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 13,
        "name": "blk.1.ffn_down.weight",
        "offset": 585409920
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 14,
        "name": "blk.1.ffn_norm.weight",
        "offset": 606053760
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 15,
        "name": "blk.1.ffn_up.weight",
        "offset": 606066048
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 16,
        "name": "blk.2.attn_norm.weight",
        "offset": 634377600
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 17,
        "name": "blk.2.attn_output.weight",
        "offset": 634389888
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 18,
        "name": "blk.2.attn_qkv.weight",
        "offset": 639698304
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 19,
        "name": "blk.2.ffn_down.weight",
        "offset": 650511744
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 20,
        "name": "blk.2.ffn_norm.weight",
        "offset": 671155584
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 21,
        "name": "blk.2.ffn_up.weight",
        "offset": 671167872
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 22,
        "name": "blk.3.attn_norm.weight",
        "offset": 699479424
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 23,
        "name": "blk.3.attn_output.weight",
        "offset": 699491712
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 24,
        "name": "blk.3.attn_qkv.weight",
        "offset": 704800128
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 25,
        "name": "blk.3.ffn_down.weight",
        "offset": 715613568
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 26,
        "name": "blk.3.ffn_norm.weight",
        "offset": 736257408
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 27,
        "name": "blk.3.ffn_up.weight",
        "offset": 736269696
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 28,
        "name": "blk.4.attn_norm.weight",
        "offset": 764581248
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 29,
        "name": "blk.4.attn_output.weight",
        "offset": 764593536
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 30,
        "name": "blk.4.attn_qkv.weight",
        "offset": 769901952
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 31,
        "name": "blk.4.ffn_down.weight",
        "offset": 780715392
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 32,
        "name": "blk.4.ffn_norm.weight",
        "offset": 794871168
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 33,
        "name": "blk.4.ffn_up.weight",
        "offset": 794883456
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 34,
        "name": "blk.5.attn_norm.weight",
        "offset": 823195008
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 35,
        "name": "blk.5.attn_output.weight",
        "offset": 823207296
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 36,
        "name": "blk.5.attn_qkv.weight",
        "offset": 828515712
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 37,
        "name": "blk.5.ffn_down.weight",
        "offset": 839329152
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 38,
        "name": "blk.5.ffn_norm.weight",
        "offset": 853484928
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 39,
        "name": "blk.5.ffn_up.weight",
        "offset": 853497216
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 40,
        "name": "blk.6.attn_norm.weight",
        "offset": 881808768
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 41,
        "name": "blk.6.attn_output.weight",
        "offset": 881821056
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 42,
        "name": "blk.6.attn_qkv.weight",
        "offset": 887129472
      },
      {
        "bits_per_elem": 6.5625,
        "byte_len": 20643840,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 14,
        "dtype_name": "Q6_K",
        "index": 43,
        "name": "blk.6.ffn_down.weight",
        "offset": 897942912
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 44,
        "name": "blk.6.ffn_norm.weight",
        "offset": 918586752
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 28311552,
        "dims": [
          3072,
          16384
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 45,
        "name": "blk.6.ffn_up.weight",
        "offset": 918599040
      },
      {
        "bits_per_elem": 32.0,
        "byte_len": 12288,
        "dims": [
          3072
        ],
        "dtype_id": 0,
        "dtype_name": "F32",
        "index": 46,
        "name": "blk.7.attn_norm.weight",
        "offset": 946910592
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 5308416,
        "dims": [
          3072,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 47,
        "name": "blk.7.attn_output.weight",
        "offset": 946922880
      },
      {
        "bits_per_elem": 5.5,
        "byte_len": 10813440,
        "dims": [
          3072,
          5120
        ],
        "dtype_id": 13,
        "dtype_name": "Q5_K",
        "index": 48,
        "name": "blk.7.attn_qkv.weight",
        "offset": 952231296
      },
      {
        "bits_per_elem": 4.5,
        "byte_len": 14155776,
        "dims": [
          8192,
          3072
        ],
        "dtype_id": 12,
        "dtype_name": "Q4_K",
        "index": 49,
        "name": "blk.7.ffn_down.weight",
        "offset": 963044736
      }
    ]
  },
  "tokenizer": {
    "bos_token_id": 199999,
    "chat_template_chars": 398,
    "eos_token_id": 200020,
    "has_chat_template": true,
    "type": "gpt2",
    "vocab_size": 200064
  }
}