Model page

TheBloke/Llama-2-7B-Chat-GGML warn

Weights only ship in a format that can run code when loaded; its license differs from its base model's. Plus 1 minor note.

downloads 265likes 873license otherarch llamaupdated 2023-09-27

claims base: meta-llama/Llama-2-7b-chat-hf · chat template: not found · view on Hugging Face ↗

Scan coverageStatic battery2026-08-26Weights battery2026-08-26Behavioral batterynot rundetails
BatteryLooks atStatus
Static batteryMetadata & packagingcomplete 2026-08-26
Weights batteryWeights forensics — no GPU, no downloadcomplete 2026-08-26no token vocabulary — pickle audit only · pickle audit clean
Behavioral batteryLive-inference differentialsnot run

Ingot runs three batteries against a model. What each one checks →

Findings

Scanned 2026-08-26 · published from a community scan.

medium Pickle-serialized weights, no safetensors

Weights ship only as pickle-based files (llama-2-7b-chat.ggmlv3.q2_K.bin, llama-2-7b-chat.ggmlv3.q3_K_L.bin, llama-2-7b-chat.ggmlv3.q3_K_M.bin, …). Loading pickle executes arbitrary code from the file — prefer a safetensors release or load in a sandbox.

How to fix

Convert the weights to safetensors before loading them anywhere that matters.

  1. Do not load the pickle files in-process — pickle deserialization executes arbitrary code from the file.
  2. Convert locally in a sandbox: `pip install safetensors` and use `safetensors.torch.save_file` on a state dict loaded with `torch.load(..., weights_only=True)` (refuses most code-execution payloads), or use Hugging Face's `convert.py` space/script.
  3. Pin the exact revision hash you converted from, and load only your converted safetensors artifact from then on.

medium License differs from claimed parent (other vs llama2)

This model declares other while its claimed base meta-llama/Llama-2-7b-chat-hf declares llama2. Verify the re-license is permitted before commercial use.

How to fix

Verify the re-license is actually permitted before relying on it.

  1. Read the parent's license for derivative-work and re-licensing terms — many open-weight licenses (e.g. Llama-family) do not permit arbitrary re-licensing.
  2. If the re-license is not permitted, the parent's terms govern your use regardless of what this repo declares.

info Pickle static analysis clean

Opcode-level parse of llama-2-7b-chat.ggmlv3.q2_K.bin, llama-2-7b-chat.ggmlv3.q3_K_L.bin, llama-2-7b-chat.ggmlv3.q3_K_M.bin, llama-2-7b-chat.ggmlv3.q3_K_S.bin (no code executed) found only standard serialization globals (0 distinct, all torch/collections/numpy). Pickle remains an executable format — this verifies the current bytes, not future uploads; prefer a safetensors release.

low Pickle checkpoint only partially analyzable

Static analysis could not fully parse: llama-2-7b-chat.ggmlv3.q2_K.bin: legacy parse stopped after 0 pickle(s): pickle: no MARK, llama-2-7b-chat.ggmlv3.q3_K_L.bin: legacy parse stopped after 0 pickle(s): pickle: no MARK, llama-2-7b-chat.ggmlv3.q3_K_M.bin: legacy parse stopped after 0 pickle(s): pickle: no MARK, +1 more. Unparsed content is unverified.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable profile of this model: measured weights-and-metadata facts, rebuilt on every scan and battery run. Updated 2026-08-26.

architecturellama
licenseother
serializationno safetensors pickle
chat templatenone
claimed lineagemeta-llama/Llama-2-7b-chat-hf
lineage verifiedunverified — weights battery pending
Full measured fingerprint
librarytransformers
pipelinetext-generation
repo files20 — pickle: llama-2-7b-chat.ggmlv3.q2_K.bin, llama-2-7b-chat.ggmlv3.q3_K_L.bin, llama-2-7b-chat.ggmlv3.q3_K_M.bin, llama-2-7b-chat.ggmlv3.q3_K_S.bin, llama-2-7b-chat.ggmlv3.q4_0.bin, llama-2-7b-chat.ggmlv3.q4_1.bin, llama-2-7b-chat.ggmlv3.q4_K_M.bin, llama-2-7b-chat.ggmlv3.q4_K_S.bin, llama-2-7b-chat.ggmlv3.q5_0.bin, llama-2-7b-chat.ggmlv3.q5_1.bin
revision76cd63c351ae
HF snapshot265 downloads · 873 likes · updated 2023-09-27 · captured 2026-08-25
weights batterytoken-embedding scan n/a — no token-embedding tensor found in the pickle checkpoint(s) — pickle checkpoint(s) statically analyzed anyway
pickle auditllama-2-7b-chat.ggmlv3.q2_K.bin, llama-2-7b-chat.ggmlv3.q3_K_L.bin, llama-2-7b-chat.ggmlv3.q3_K_M.bin, llama-2-7b-chat.ggmlv3.q3_K_S.bin0 standard global(s) · legacy (pre-1.6) format, head-scan only
Battery runs (1)the run trace behind the findings — what each job measured
batterystatusqueueddurationattempts
weightscomplete2026-08-25 21:4913s1
weights run 2026-08-25 measurements
probes runpickle-static-analysis

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/TheBloke/Llama-2-7B-Chat-GGML/badge.svg)](https://ingot.tools/models/TheBloke/Llama-2-7B-Chat-GGML)
Gate it in CI