初始化项目，由ModelHub XC社区提供模型

Model: ericflo/Llama-3.2-1B-Instruct-RLHF-v0.1 Source: Original Platform
2026-05-26 10:24:18 +08:00
commit f763b65a0f
13 changed files with 2247 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,41 @@
+*.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
+Llama-3.2-1B-Instruct-RLHF-v0.1-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-RLHF-v0.1-F32.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-RLHF-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-RLHF-v0.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.2-1B-Instruct-RLHF-v0.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3.2-1B-Instruct-RLHF-v0.1-BF16.gguf
+++ b/Llama-3.2-1B-Instruct-RLHF-v0.1-BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:214b7d444579e70c39702428ebb1a66ff66b6bdfa2dabea6916c4af3860683aa
+size 2479595168
--- a/Llama-3.2-1B-Instruct-RLHF-v0.1-F32.gguf
+++ b/Llama-3.2-1B-Instruct-RLHF-v0.1-F32.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af05e91a54f203ad597cfae180ee47a414779e42e6e8a7b477fce58771854c62
+size 4951088800
--- a/Llama-3.2-1B-Instruct-RLHF-v0.1-Q4_K_M.gguf
+++ b/Llama-3.2-1B-Instruct-RLHF-v0.1-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:677a5935fc80e4ef0a1875d9e63df558d42cb626fb00554674b1097f2b280352
+size 807693984
--- a/Llama-3.2-1B-Instruct-RLHF-v0.1-Q6_K.gguf
+++ b/Llama-3.2-1B-Instruct-RLHF-v0.1-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb89869a4c75671d97d1fc607af7ffe9fdfa1da5a3d74ca04218ef989fff4ad
+size 1021800096
--- a/Llama-3.2-1B-Instruct-RLHF-v0.1-Q8_0.gguf
+++ b/Llama-3.2-1B-Instruct-RLHF-v0.1-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441c5cc0b8c27827451848aac1bdf9fac30519cecbfa2ee75d1eb03421b5259f
+size 1321082528
--- a/README.md
+++ b/README.md
@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+datasets:
+- OpenRLHF/prompt-collection-v0.1
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+library_name: transformers
+---
+
+# This model's benchmark results
+
+|      Tasks      |Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
+|-----------------|-------|----------------|-----:|-----------|---|-----:|---|------|
+|tinyBenchmarks   |    N/A|                |      |           |   |      |   |      |
+| - tinyArc       |      0|none            |    25|acc_norm   |↑  |0.4253|±  |   N/A|
+| - tinyGSM8k     |      0|flexible-extract|     5|exact_match|↑  |0.3768|±  |   N/A|
+|                 |       |strict-match    |     5|exact_match|↑  |0.3768|±  |   N/A|
+| - tinyHellaswag |      0|none            |    10|acc_norm   |↑  |0.5379|±  |   N/A|
+| - tinyMMLU      |      0|none            |     0|acc_norm   |↑  |0.4483|±  |   N/A|
+| - tinyTruthfulQA|      0|none            |     0|acc        |↑  |0.4217|±  |   N/A|
+| - tinyWinogrande|      0|none            |     5|acc_norm   |↑  |0.5366|±  |   N/A|
+
+# Original `meta-llama/Llama-3.2-1B-Instruct` benchmark results
+
+|      Tasks      |Version|     Filter     |n-shot|  Metric   |   |Value |   |Stderr|
+|-----------------|-------|----------------|-----:|-----------|---|-----:|---|------|
+|tinyBenchmarks   |    N/A|                |      |           |   |      |   |      |
+| - tinyArc       |      0|none            |    25|acc_norm   |↑  |0.4145|±  |   N/A|
+| - tinyGSM8k     |      0|flexible-extract|     5|exact_match|↑  |0.3412|±  |   N/A|
+|                 |       |strict-match    |     5|exact_match|↑  |0.3412|±  |   N/A|
+| - tinyHellaswag |      0|none            |    10|acc_norm   |↑  |0.5335|±  |   N/A|
+| - tinyMMLU      |      0|none            |     0|acc_norm   |↑  |0.4298|±  |   N/A|
+| - tinyTruthfulQA|      0|none            |     0|acc        |↑  |0.4288|±  |   N/A|
+| - tinyWinogrande|      0|none            |     5|acc_norm   |↑  |0.5366|±  |   N/A|
+
+Below is a side-by-side comparison of the two result sets. For each task, the higher value (i.e., “better” on that metric) is highlighted in **bold**:
+
+|      Task          | this   | orig   | Better?                |
+|--------------------|--------|--------|------------------------|
+| tinyArc (acc_norm) | **0.4253** | 0.4145 | v1 higher            |
+| tinyGSM8k (exact_match) | **0.3768** | 0.3412 | v1 higher            |
+| tinyHellaswag (acc_norm) | **0.5379** | 0.5335 | v1 higher            |
+| tinyMMLU (acc_norm) | **0.4483** | 0.4298 | v1 higher            |
+| tinyTruthfulQA (acc)    | 0.4217 | **0.4288** | v2 higher            |
+| tinyWinogrande (acc_norm) | 0.5366 | 0.5366 | tie                  |
+
+### Observations
+1. **Ours outperforms the original on four tasks** (tinyArc, tinyGSM8k, tinyHellaswag, tinyMMLU).
+2. **The original outperforms ours on one task** (tinyTruthfulQA).
+3. One task is a **tie** (tinyWinogrande).
+
+Given these comparisons, **our results are stronger overall** because it has higher scores on the majority of tasks. The only exception is on tinyTruthfulQA, where the original scores slightly better, and on tinyWinogrande, both versions tie.
--- a/config.json
+++ b/config.json
@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.3"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cde2b08322b083365c0ed193dc3bf475e7f574616e5e5d352a6fc1c728aded4
+size 2471645608
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52716f60c3ad328509fa37cdded9a2f1196ecae463f5480f5d38c66a25e7a7dc
+size 17210019
--- a/tokenizer_config.json
+++ b/tokenizer_config.json