SueMintony commited on
Commit
67e487c
·
verified ·
1 Parent(s): 22a61f9

Rename CLAMP checkpoint release references

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  - ctrlg
7
  - constrained-decoding
8
  ---
9
- # CLAMP HMM checkpoints
10
 
11
  Neural-HMM priors trained on Llama-3.1 continuation samples for two EAI
12
  datasets (BEHAVIOR and VirtualHome). Used by `eai_ctrlg` as the semantic
@@ -41,7 +41,7 @@ The checkpoint passed its recorded training and reload validation gates. No down
41
  ## Related data and code
42
 
43
  - Code: [HLR/CLAMP](https://github.com/HLR/CLAMP)
44
- - VLABench demonstrations: [SueMintony/CLAMP Dataset](https://huggingface.co/datasets/SueMintony/CLAMP)
45
  - Release collection: [CLAMP — Code, Model, and Dataset](https://huggingface.co/collections/SueMintony/clamp-code-model-and-dataset-6a876ddfa7602097020a565c)
46
 
47
  <!-- CLAMP_TRAINING_ARTIFACTS_START -->
@@ -49,8 +49,8 @@ The checkpoint passed its recorded training and reload validation gates. No down
49
 
50
  The full, machine-readable pairing of every checkpoint and sampled-continuation artifact is in [`release_catalog.json`](release_catalog.json).
51
 
52
- - **Qwen3.5-9B:** 10 archived HMM checkpoints under [`trained/qwen3.5-9b/`](trained/qwen3.5-9b) — combined BEHAVIOR and VirtualHome variants plus four task-specific variants per domain. Their continuation files are in the [Dataset repository](https://huggingface.co/datasets/SueMintony/CLAMP/tree/main/sampled-continuations/qwen3.5-9b).
53
- - **InternVL3.5-8B:** IV35-H2-S5 formal EQX checkpoint, portable NPZ export, and [2,926 sampled records](https://huggingface.co/datasets/SueMintony/CLAMP/tree/main/sampled-continuations/internvl3.5-8b/iv35-h2-s5).
54
  - **Qwen3-VL-8B-Instruct:** [compatibility-remapped HMM](compatibility/qwen3-vl-8b-instruct/behavior/hmm-h128-remapped/checkpoint.eqx). It is a vocabulary remap of a historical HMM, not a retrained model, and has no local sampled-continuation artifact.
55
 
56
  The public continuation release contains token arrays / sampled outputs and length metadata only; it excludes original prompts, scene assets, and benchmark data.
 
6
  - ctrlg
7
  - constrained-decoding
8
  ---
9
+ # CLAMP HMM Checkpoints
10
 
11
  Neural-HMM priors trained on Llama-3.1 continuation samples for two EAI
12
  datasets (BEHAVIOR and VirtualHome). Used by `eai_ctrlg` as the semantic
 
41
  ## Related data and code
42
 
43
  - Code: [HLR/CLAMP](https://github.com/HLR/CLAMP)
44
+ - VLABench demonstrations: [SueMintony/CLAMP-Sampled-Continuations-and-Demos](https://huggingface.co/datasets/SueMintony/CLAMP-Sampled-Continuations-and-Demos)
45
  - Release collection: [CLAMP — Code, Model, and Dataset](https://huggingface.co/collections/SueMintony/clamp-code-model-and-dataset-6a876ddfa7602097020a565c)
46
 
47
  <!-- CLAMP_TRAINING_ARTIFACTS_START -->
 
49
 
50
  The full, machine-readable pairing of every checkpoint and sampled-continuation artifact is in [`release_catalog.json`](release_catalog.json).
51
 
52
+ - **Qwen3.5-9B:** 10 archived HMM checkpoints under [`trained/qwen3.5-9b/`](trained/qwen3.5-9b) — combined BEHAVIOR and VirtualHome variants plus four task-specific variants per domain. Their continuation files are in the [Dataset repository](https://huggingface.co/datasets/SueMintony/CLAMP-Sampled-Continuations-and-Demos/tree/main/sampled-continuations/qwen3.5-9b).
53
+ - **InternVL3.5-8B:** IV35-H2-S5 formal EQX checkpoint, portable NPZ export, and [2,926 sampled records](https://huggingface.co/datasets/SueMintony/CLAMP-Sampled-Continuations-and-Demos/tree/main/sampled-continuations/internvl3.5-8b/iv35-h2-s5).
54
  - **Qwen3-VL-8B-Instruct:** [compatibility-remapped HMM](compatibility/qwen3-vl-8b-instruct/behavior/hmm-h128-remapped/checkpoint.eqx). It is a vocabulary remap of a historical HMM, not a retrained model, and has no local sampled-continuation artifact.
55
 
56
  The public continuation release contains token arrays / sampled outputs and length metadata only; it excludes original prompts, scene assets, and benchmark data.