RL-MPQ High_Fidelity — 2026-06-11T15:29:08.676886

High_Fidelity/README.md

@@ -0,0 +1,45 @@
+---
+license: llama2
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+  - rl-mpq
+  - mixed-precision
+  - quantization
+library_name: transformers
+---
+
+# LLAMA-2-7B — High Fidelity
+
+Subfolder of [`AvoCahDoe/llama-2-7b-rlmpq`](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq) (all RL-MPQ scenarios for this model).
+
+Fake-quantized weights for **High_Fidelity** applied to
+[meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) (per-layer asymmetric group-wise quant, group_size=128).
+
+## Load
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo = "AvoCahDoe/llama-2-7b-rlmpq"
+model = AutoModelForCausalLM.from_pretrained(repo, subfolder="High_Fidelity", torch_dtype="float16")
+tokenizer = AutoTokenizer.from_pretrained(repo, subfolder="High_Fidelity")
+```
+
+## Metrics
+
+| Metric | Value |
+|--------|-------|
+| Scenario | High_Fidelity |
+| Average bits per weight | 6.5 |
+| Compression ratio (vs FP16) | 2.4615x |
+| WikiText-2 perplexity | 4.9808 |
+| Layers | 32 |
+| Bit distribution | {'4': 12, '8': 20} |
+
+## Policy (bits per layer)
+
+```
+[8, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8]
+```
+
+Generated: 2026-06-11T15:29:08.289209

High_Fidelity/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default",
+    "type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.11.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

High_Fidelity/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.11.0"
+}

High_Fidelity/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae9da6880e3eac25d0ba6965603254cc70c9199def508ec9d49334af21fdcd1
+size 13476864944

High_Fidelity/rlmpq_policy.json

@@ -0,0 +1,60 @@
+{
+  "slug": "llama_2_7b",
+  "hf_id": "meta-llama/Llama-2-7b-hf",
+  "scenario": "High_Fidelity",
+  "params": {
+    "lambda_mse": 1.0,
+    "lambda_bit": 0.05,
+    "max_mse_clip": 1.0,
+    "target_bits": 7.0,
+    "lambda_budget": 2.0
+  },
+  "policy": [
+    8,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    4,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8,
+    8
+  ],
+  "num_layers": 32,
+  "avg_bits": 6.5,
+  "total_reward": -1.919881,
+  "compression_ratio": 2.4615,
+  "approx_size_gb": 5.688,
+  "bit_distribution": {
+    "4": 12,
+    "8": 20
+  },
+  "avg_mse_per_bit": {
+    "8": 0.00020028,
+    "4": 0.36544608
+  },
+  "validation_elapsed_s": 0.0169
+}

High_Fidelity/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}