初始化项目，由ModelHub XC社区提供模型

Model: llmware/slim-topics
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 +1,90 @@
+---
+license: apache-2.0  
+inference: false  
+---
+
+# SLIM-TOPICS
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+**slim-topics** is part of the SLIM ("**S**tructured **L**anguage **I**nstruction **M**odel") model series, consisting of small, specialized decoder-based models, fine-tuned for function-calling.  
+
+slim-sentiment has been fine-tuned for **topic analysis** function calls, generating output consisting of a python dictionary corresponding to specified keys, e.g.:  
+
+&nbsp;&nbsp;&nbsp;&nbsp;`{"topics": ["..."]}`
+
+
+SLIM models are designed to generate structured outputs that can be used programmatically as part of a multi-step, multi-model LLM-based automation workflow.  
+
+Each slim model has a 'quantized tool' version, e.g.,  [**'slim-topics-tool'**](https://huggingface.co/llmware/slim-topics-tool).  
+
+
+## Prompt format:
+
+`function = "classify"`  
+`params = "topics"`  
+`prompt = "<human> " + {text} + "\n" + `  
+&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; &nbsp; &nbsp; &nbsp;`"<{function}> " + {params} + "</{function}>" + "\n<bot>:"`  
+
+
+<details>
+<summary>Transformers Script </summary>
+
+    model = AutoModelForCausalLM.from_pretrained("llmware/slim-topics")
+    tokenizer = AutoTokenizer.from_pretrained("llmware/slim-topics")
+
+    function = "classify"
+    params = "topic"
+
+    text = "The stock market declined yesterday as investors worried increasingly about the slowing economy."  
+    
+    prompt = "<human>: " + text + "\n" + f"<{function}> {params} </{function}>\n<bot>:"
+
+    inputs = tokenizer(prompt, return_tensors="pt")
+    start_of_input = len(inputs.input_ids[0])
+
+    outputs = model.generate(
+        inputs.input_ids.to('cpu'),
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        temperature=0.3,
+        max_new_tokens=100
+    )
+
+    output_only = tokenizer.decode(outputs[0][start_of_input:], skip_special_tokens=True)
+
+    print("output only: ", output_only)  
+
+    # here's the fun part
+    try:
+        output_only = ast.literal_eval(llm_string_output)
+        print("success - converted to python dictionary automatically")
+    except:
+        print("fail - could not convert to python dictionary automatically - ", llm_string_output)
+   
+   </details>  
+ 
+<details>  
+
+
+
+    
+<summary>Using as Function Call in LLMWare</summary>
+
+    from llmware.models import ModelCatalog
+    slim_model = ModelCatalog().load_model("llmware/slim-topics")
+    response = slim_model.function_call(text,params=["topics"], function="classify")
+
+    print("llmware - llm_response: ", response)
+
+</details>  
+
+    
+## Model Card Contact
+
+Darren Oberst & llmware team  
+
+[Join us on Discord](https://discord.gg/MhZn5Nc39h)
+
+

config.json

@@ -0,0 +1,89 @@
+{
+  "aib_version": "model_archive_122723_tiny_llama-1.1b-29",
+  "training_dataset": [
+    "aib_label_samples_524s.jsonl"
+  ],
+  "training_timestamp": "Wed Dec 27 17:43:21 2023",
+  "training_comments": "tiny-llama-1.1b-27",
+  "vocab_size": 32000,
+  "max_position_embeddings": 2048,
+  "hidden_size": 2048,
+  "intermediate_size": 5632,
+  "num_hidden_layers": 22,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 4,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "pretraining_tp": 1,
+  "use_cache": true,
+  "rope_theta": 10000.0,
+  "rope_scaling": null,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": "float32",
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": false,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "chunk_size_feed_forward": 0,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 1,
+  "pad_token_id": null,
+  "eos_token_id": 2,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T",
+  "transformers_version": "4.36.1",
+  "model_type": "llama",
+  "trained": "custom training"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "max_length": 2048,
+  "transformers_version": "4.31.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac097221204bc48e76b83fb5151f94e385163e0a030083c7081fc5dcacbff9f
+size 2200181102

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}