初始化项目，由ModelHub XC社区提供模型

Model: opencerebral/Boris-1.3-75M-Instruct
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+Boris-75M.png filter=lfs diff=lfs merge=lfs -text
+Boris-1.3-75M.png filter=lfs diff=lfs merge=lfs -text
+benchmarks.png filter=lfs diff=lfs merge=lfs -text

Boris-1.3-75M.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c872c8f0f655c2e60c1f807ef125ff6913063431c5eede951c1b017c219da3
+size 783476

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+datasets:
+- HuggingFaceFW/fineweb-edu
+- mlfoundations/dclm-baseline-1.0-parquet
+- HuggingFaceTB/smol-smoltalk
+tags:
+- boris
+- nmai
+- gpt2
+- 75M
+- instruct
+base_model:
+- KSP-NMAI/Boris-1.3-75M
+---
+ 
+![Boris](Boris-1.3-75M.png)
+ 
+# Boris-1.3-75M-Instruct
+ 
+Boris-1.3-75M-Instruct is a 75 million-parameter language model created by New
+Millennium Artificial Intelligence (NMAI).
+ 
+This is an **instruction-tuned model**. It follows instructions and holds a
+conversation. For the base (pretrained-only) version, see
+[KSP-NMAI/Boris-1.3-75M](https://huggingface.co/KSP-NMAI/Boris-1.3-75M).
+ 
+## Usage
+ 
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+ 
+tok = AutoTokenizer.from_pretrained("KSP-NMAI/Boris-1.3-75M-Instruct")
+model = AutoModelForCausalLM.from_pretrained("KSP-NMAI/Boris-1.3-75M-Instruct")
+ 
+messages = [{"role": "user", "content": "What's a good way to start learning C?"}]
+ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+out = model.generate(ids, max_new_tokens=120, do_sample=True, top_p=0.95)
+print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))
+```
+ 
+## Details
+ 
+| | |
+|---|---|
+| Architecture | GPT-2 (pre-LN, learned positional embeddings, tied embeddings) |
+| Layers / heads / d_model | 12 / 9 / 576 |
+| Context length | 1024 |
+| Vocab | 50304 (GPT-NeoX-20B BPE, padded) |
+| Tokenizer | `EleutherAI/gpt-neox-20b` |
+| Precision | trained in bf16 autocast with fp32 master weights |
+ 
+## Fine-tuning
+ 
+Fine-tuned on [smol-smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smol-smoltalk) and [OpenAssistant](https://huggingface.co/datasets/OpenAssistant/oasst1) for *279,815* examples over *8:19:30* on one RTX 3060.
+ 
+| | |
+|---|---|
+| Final loss | *1.4162* |
+| Final grad norm | *1.185* |
+| Final learning rate | *1.00e-05* |
+ 
+![Benchmarks](benchmarks.png)
+ 
+## Limitations
+ 
+A model of this size will produce text that is frequently inaccurate,
+inconsistent, or offensive. It has received no alignment or safety tuning and
+should not be used for factual reference or deployed without supervision.
+ 
+## Copyright & License
+ 
+*Copyright 2026 Joseph Jones*
+ 
+This project and all associated files (the "Work") are licensed under the Apache
+License, Version 2.0 (the "License"); you may not use this project except in
+compliance with the License. You may obtain a copy of the License at:
+ 
+    http://www.apache.org/licenses/LICENSE-2.0
+ 
+Unless required by applicable law or agreed to in writing, software distributed
+under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.

benchmarks.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb9e4300acca79c53167b65c655b180ec77f2b3a3ed8744350d3c71582141cc
+size 186997

config.json

@@ -0,0 +1,35 @@
+{
+  "activation_function": "gelu",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 576,
+  "n_head": 9,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": null,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.13.1",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fee1ba947d5603c7d9297dc69830d7f1db9b8afa4c2bffbbe7060d9f4b73ed5
+size 309741640

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<|endoftext|>",
+  "chat_template": "{%- set ns = namespace(sys='') -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.sys = (message['content'] | trim) -%}{%- elif message['role'] == 'user' -%}{%- set instr = (message['content'] | trim) -%}{%- if ns.sys -%}{%- set instr = ns.sys + '\n\n' + instr -%}{%- set ns.sys = '' -%}{%- endif -%}{{- 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n' + instr + '\n\n### Response:\n' -}}{%- elif message['role'] == 'assistant' -%}{{- ' ' + (message['content'] | trim) + '<|endoftext|>' -}}{%- endif -%}{%- endfor -%}"
+}