初始化项目，由ModelHub XC社区提供模型

Model: sasa2000/granite-3.1-1b-a400m-instruct-reap-pruned-010
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,45 @@
+---
+base_model: ibm-granite/granite-3.1-1b-a400m-instruct
+pipeline_tag: text-generation
+tags:
+- granite
+- reap
+- pruning
+- multilingual
+license: apache-2.0
+---
+
+# Granite 3.1 1B A400M Instruct REAP Pruned Checkpoint
+
+This repository contains a REAP layerwise-pruned checkpoint of
+`ibm-granite/granite-3.1-1b-a400m-instruct`.
+
+## Base Model
+
+- Model: `ibm-granite/granite-3.1-1b-a400m-instruct`
+- Architecture: `GraniteMoeForCausalLM`
+- `num_local_experts=32`
+- `num_experts_per_tok=8`
+
+## Pruning Setup
+
+- Dataset: `theblackcat102/evol-codealpaca-v1`
+- `model_max_length=2048`
+- `batches_per_category=128`
+- `batch_size=1`
+- `batch_group_size=8`
+- `renormalize_router_weights=true`
+- `truncate=false`
+
+## Checkpoint
+
+- Requested ratio: `0.10`
+- Experts pruned: `3`
+- Experts retained: `29`
+- Actual ratio: `9.38%`
+- Local output dir: `layerwise_reap-renorm_true-seed_42-0.09`
+
+## Provenance
+
+- Created with Codex using GPT-5.5.
+- Generated for the REAP pruning experiment log and multilingual evaluation.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end_of_role|>": 49153,
+  "<|start_of_role|>": 49152,
+  "<|tool_call|>": 49154
+}

chat_template.jinja

@@ -0,0 +1,64 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "Knowledge Cutoff Date: April 2024.
+Today's Date: " + strftime_now('%B %d, %Y') + ".
+You are Granite, developed by IBM." %}
+    {%- if tools and documents %}
+        {%- set system_message = system_message + " You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.
+
+Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- elif tools %}
+        {%- set system_message = system_message + " You are a helpful AI assistant with access to the following tools. When a tool is required to answer the user's query, respond with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request." %}
+    {%- elif documents %}
+        {%- set system_message = system_message + " Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data." %}
+    {%- else %}
+        {%- set system_message = system_message + " You are a helpful AI assistant." %}    
+    {%- endif %}
+    {%- if 'citations' in controls and documents %}
+        {%- set system_message = system_message + '
+
+In your response, use the symbols <co> and </co> to indicate when a fact comes from a document in the search result, e.g <co>0</co> for a fact from document 0. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}
+    {%- endif %}
+    {%- if 'hallucinations' in controls and documents %}
+        {%- set system_message = system_message + '
+
+Finally, after the response is written, include a numbered list of sentences from the response that are potentially hallucinated and not based in the documents.' %}
+    {%- endif %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>
+' }}
+{%- if tools %}
+    {{- '<|start_of_role|>tools<|end_of_role|>' }}
+    {{- tools | tojson(indent=4) }}
+    {{- '<|end_of_text|>
+' }}
+{%- endif %}
+{%- if documents %}
+    {{- '<|start_of_role|>documents<|end_of_role|>' }}
+    {%- for document in documents %}
+        {{- 'Document ' + loop.index0 | string + '
+' }}
+        {{- document['text'] }}
+        {%- if not loop.last %}
+            {{- '
+
+'}}
+        {%- endif%}
+    {%- endfor %}
+    {{- '<|end_of_text|>
+' }}
+{%- endif %}
+{%- for message in loop_messages %}
+    {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>
+' }}
+    {%- if loop.last and add_generation_prompt %}
+        {{- '<|start_of_role|>assistant' }}
+            {%- if controls %}
+                {{- ' ' + controls | tojson()}}
+            {%- endif %}
+        {{- '<|end_of_role|>' }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "GraniteMoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.015625,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "logits_scaling": 6.0,
+  "max_position_embeddings": 131072,
+  "model_type": "granitemoe",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 29,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "position_embedding_type": "rope",
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1500000.0,
+  "router_aux_loss_coef": 0.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 49155
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.55.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4360268e6506298981a62f20f8fd5c9004980b90da937544cae9f0929ecc8e57
+size 2442643208

reap_args.yaml

@@ -0,0 +1,81 @@
+cluster_args:
+  cluster_description: null
+  cluster_method: agglomerative
+  compression_ratio: 0.1
+  expert_sim: ttm
+  frequency_penalty: true
+  linkage_method: average
+  max_cluster_size: null
+  multi_layer: null
+  num_clusters: null
+  singleton_outlier_experts: false
+  singleton_super_experts: false
+  softmax_temperature: null
+ds_args:
+  dataset_config_name: null
+  dataset_name: theblackcat102/evol-codealpaca-v1
+  dataset_test_split: test
+  shuffle: true
+  split: train
+eval_args:
+  evalplus_tasks:
+  - mbpp
+  - humaneval
+  greedy: true
+  lm_eval_tasks:
+  - winogrande
+  - arc_challenge
+  - arc_easy
+  - boolq
+  - hellaswag
+  - mmlu
+  - openbookqa
+  - rte
+  min_p: 0.0
+  parallel_tasks: 32
+  results_dir: null
+  run_evalplus: true
+  run_livecodebench: true
+  run_lm_eval: true
+  run_math: false
+  run_wildbench: false
+  server_log_file_name: server.log
+  temperature: 0.7
+  top_k: 20
+  top_p: 0.8
+  use_server: true
+  vllm_port: 8000
+layerwise_args:
+  batch_group_size: 8
+  low_cpu_mem_usage: true
+  save_intermediate: false
+model_args:
+  model_name: ibm-granite/granite-3.1-1b-a400m-instruct
+  num_experts_per_tok_override: null
+obs_args:
+  batch_size: 1
+  batches_per_category: 128
+  distance_measure: angular
+  model_max_length: 2048
+  output_file_name: observations_granite_1b_128x2048_reap.pt
+  overwrite_observations: false
+  record_pruning_metrics_only: true
+  renormalize_router_weights: true
+  return_vllm_tokens_prompt: false
+  select_only_categories: null
+  split_by_category: false
+  truncate: false
+prune_args:
+  n_experts_to_prune: null
+  overwrite_pruned_model: false
+  perserve_outliers: false
+  perserve_super_experts: false
+  prune_method: reap
+reap_args:
+  debug: false
+  do_eval: false
+  plot_clusters: false
+  profile: true
+  run_observer_only: false
+  seed: 42
+  smoke_test: false

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,198 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|start_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49153": {
+      "content": "<|end_of_role|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49154": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|start_of_role|>",
+    "<|end_of_role|>",
+    "<|tool_call|>"
+  ],
+  "bos_token": "<|end_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|end_of_text|>",
+  "vocab_size": 49152
+}