初始化项目，由ModelHub XC社区提供模型

Model: AlienKevin/marin-8b-instruct-sft-terminalcorpus
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: marin-community/marin-8b-instruct
+datasets:
+  - nvidia/Nemotron-Terminal-Corpus
+tags:
+  - terminal
+  - agentic
+  - sft
+  - llama
+  - marin
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+# Marin-8B-Instruct SFT on TerminalCorpus
+
+Marin-8B Instruct fine-tuned on [nvidia/Nemotron-Terminal-Corpus](https://huggingface.co/datasets/nvidia/Nemotron-Terminal-Corpus) (366K terminal agent trajectories).
+
+## Model Details
+
+| Parameter | Value |
+|---|---|
+| Base model | [marin-community/marin-8b-instruct](https://huggingface.co/marin-community/marin-8b-instruct) |
+| Architecture | Llama 3 8B (32 layers, 4096 hidden, 32 heads, 8 KV heads) |
+| Tokenizer | [marin-community/marin-tokenizer](https://huggingface.co/marin-community/marin-tokenizer) |
+| Training data | nvidia/Nemotron-Terminal-Corpus (366K examples, all 4 subsets) |
+| Epochs | 2 |
+| Training steps | 5,721 |
+| Batch size | 128 |
+| Sequence length | 32,768 |
+| Learning rate | 2e-5 (cosine, 10% warmup) |
+| Optimizer | AdamW (β=0.9/0.95), grad_clip=1.0, wd=1e-4 |
+| TPU | v5p-64 |
+| Final loss | 0.442 |
+
+## Evaluation Results
+
+### Terminal-Bench 2.0
+
+| Model | TB2 Accuracy |
+|---|---|
+| Marin-8B Instruct (no SFT) | 0/89 = 0% |
+| **Marin-8B Instruct + TerminalCorpus SFT** | **1/89 = 1.1%** |
+| NemotronTerminal-8B (Qwen3-8B, paper) | 13.0% ± 2.2 |
+| Marin Qwen3-8B SFT reproduction (exp3490b) | 14/88 = 15.9% |
+
+### TBLite Progression
+
+| Checkpoint | TBLite |
+|---|---|
+| Step 1500 (26%) | 1/100 = 1% |
+| Step 3000 (52%) | 5/100 = 5% |
+
+## Training Details
+
+Trained following the [NemotronTerminal-8B](https://arxiv.org/abs/2602.21193) paper hyperparameters. The model reaches a higher final loss (0.442 vs 0.360) as the Qwen3-8B reproduction but scores significantly lower on terminal benchmarks, likely due to architecture and tokenizer differences between Llama 3 and Qwen3.
+
+Tracked in: [marin-community/marin#4420](https://github.com/marin-community/marin/issues/4420)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("AlienKevin/marin-8b-instruct-sft-terminalcorpus")
+tokenizer = AutoTokenizer.from_pretrained("AlienKevin/marin-8b-instruct-sft-terminalcorpus")
+```
+
+## License
+
+Apache 2.0

chat_template.jinja

@@ -0,0 +1,149 @@
+{{ bos_token }}
+{%- if enable_thinking is defined -%}
+  {%- if enable_thinking is sameas true -%}
+    {%- set _reasoning_mode = "/think" -%}
+  {%- elif enable_thinking is sameas false -%}
+    {%- set _reasoning_mode = "/nothink" -%}
+  {%- else -%}
+    {%- set _reasoning_mode = enable_thinking -%}
+  {%- endif -%}
+{%- else -%}
+  {%- set _reasoning_mode = none -%}
+{%- endif -%}
+{%- set _custom_instructions = custom_instructions | default(None, true) -%}
+{%- set _xml_tools_list = xml_tools | default([], true) -%}
+{%- if tools is defined and tools -%}
+  {%- set _xml_tools_list = tools -%}
+{%- endif -%}
+{%- set _python_tools = python_tools | default([], true) -%}
+{%- set _has_aux_header = (_reasoning_mode is not none) or _custom_instructions or (_xml_tools_list) or (_python_tools) -%}
+{%- if _has_aux_header -%}
+<|start_header_id|>system<|end_header_id|>
+{%- if _reasoning_mode is not none -%}
+Reasoning: {{ _reasoning_mode }}
+{%- endif %}
+{%- if _custom_instructions %}
+{{ _custom_instructions | trim }}
+{%- endif %}
+{% if _xml_tools_list or _python_tools %}
+{{ "
+### Tools
+" }}
+You may call one or more functions to assist with the user query.
+{% if _xml_tools_list %}
+You are provided with function signatures within <tools> </tools> tags:
+
+<tools>
+{% for tool in _xml_tools_list %}
+{{ tool | string }}{% if not loop.last %}
+{% endif %}
+{% endfor %}
+</tools>
+
+For each function call, pass a json object with function name and arguments within <tool_call> </tool_call> tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+
+{% endif %}
+{% if _python_tools %}
+When you send a message containing Python code between <|python_tag|> and <|eom_id|> tags, it will be executed in a stateful Jupyter notebook environment, and you will then be given the output.
+
+You can use the following tools in your python code like regular functions:
+<tools>
+{% for tool in _python_tools %}
+{{ tool | string }}{% if not loop.last %}
+{% endif %}
+{% endfor %}
+</tools>
+{% endif %}
+{% endif %}
+<|eot_id|>
+{%- endif -%}
+{%- for message in messages -%}
+  {%- set has_tool_calls = message.get('tool_calls') is not none and message.get('tool_calls') -%}
+  {%- if not (message.get('role') in ['tool', 'ipython'] or has_tool_calls) -%}
+    {%- if message.get('role') == 'assistant' -%}
+<|start_header_id|>assistant<|end_header_id|>
+{% set content = message.get('content') %}
+{% if content is string %}
+{% generation %}{{- content | trim }}<|eot_id|>{% endgeneration %}
+{% elif content is mapping %}
+{% generation %}{{- content.get('text', '') | trim }}<|eot_id|>{% endgeneration %}
+{% elif content is iterable %}
+{% generation %}
+{%- for chunk in content -%}
+  {%- if chunk.get('type') == 'text' -%}
+    {{ chunk.get('text', '') | trim }}
+  {%- endif -%}
+{%- endfor -%}
+<|eot_id|>
+{% endgeneration %}
+{% else %}
+{% generation %}{% endgeneration %}<|eot_id|>
+{% endif %}
+    {%- else -%}
+<|start_header_id|>{{ message['role'] }}<|end_header_id|>
+{% set content = message.get('content') %}
+{% if content is string %}
+{{ content | trim }}<|eot_id|>
+{% elif content is mapping %}
+{{ content.get('text', '') | trim }}<|eot_id|>
+{% elif content is iterable %}
+{%- for chunk in content -%}
+  {%- if chunk.get('type') == 'text' -%}
+    {{ chunk.get('text', '') | trim }}
+  {%- endif -%}
+{%- endfor -%}<|eot_id|>
+{% else %}
+<|eot_id|>
+{% endif %}
+    {%- endif -%}
+
+  {%- elif message.get('role') == 'tool' -%}
+    {%- set _tool_name = message.get('name') -%}
+    {%- set _tool_id = message.get('tool_call_id') -%}
+    {%- set _attr_name = ' name="' ~ _tool_name ~ '"' if _tool_name else '' -%}
+    {%- set _attr_id = ' id="' ~ _tool_id ~ '"' if _tool_id else '' -%}
+<|start_header_id|>tool<|end_header_id|>
+<tool_response{{ _attr_name }}{{ _attr_id }}>
+{%- set tool_content = message.get('content') -%}
+{%- if tool_content is mapping or (tool_content is iterable and tool_content is not string) -%}
+{{- tool_content | tojson }}
+{%- else -%}
+{{- tool_content if tool_content is not none else '' }}
+{%- endif -%}
+</tool_response><|eot_id|>
+{{- "
+" -}}
+  {%- elif message.get('role') == 'ipython' -%}
+<|start_header_id|>ipython<|end_header_id|>
+{% set ipy_content = message.get('content') %}
+{% if ipy_content is string %}
+{{- { "output": ipy_content } | tojson -}}
+{% elif ipy_content is iterable %}
+{%- for chunk in ipy_content -%}
+  {%- if chunk.get('type') == 'text' -%}
+    {{- { "output": chunk.get('text', '') } | tojson -}}
+  {%- endif -%}
+{%- endfor -%}
+{% else %}
+{{- { "output": ipy_content } | tojson -}}
+{% endif %}
+<|eot_id|>
+{% elif has_tool_calls -%}
+    {%- if message.tool_calls|length != 1 -%}
+      {{- raise_exception("This template expects exactly one tool call per assistant turn.") -}}
+    {%- endif -%}
+    {%- set tool_call = message.tool_calls[0].function -%}
+<|start_header_id|>assistant<|end_header_id|>
+{% generation %}
+{{- '{"name": "' + tool_call.name + '", "arguments": ' -}}
+{{- tool_call.arguments | tojson -}}
+{{- "}" -}}<|eot_id|>
+{% endgeneration %}
+  {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+<|start_header_id|>assistant<|end_header_id|>
+{% endif -%}

config.json

@@ -0,0 +1,94 @@
+{
+  "vocab_size": 128256,
+  "max_position_embeddings": 32768,
+  "hidden_size": 4096,
+  "intermediate_size": 14336,
+  "num_hidden_layers": 32,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "pretraining_tp": 1,
+  "use_cache": true,
+  "rope_theta": 500000,
+  "rope_scaling": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "mlp_bias": false,
+  "head_dim": 128,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "dtype": null,
+  "pruned_heads": {},
+  "tie_word_embeddings": false,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 128000,
+  "pad_token_id": null,
+  "eos_token_id": 128009,
+  "sep_token_id": null,
+  "decoder_start_token_id": 128000,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "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,
+  "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": [
+    128000,
+    128001
+  ],
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "_name_or_path": "",
+  "transformers_version": "4.57.3",
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "model_type": "llama",
+  "output_attentions": false,
+  "torch_dtype": "bfloat16"
+}

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": "4.42.3"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642f3835c55b922d35dcbfa59ac404b12477dcacdedfdb28fdc8934bc5e5462f
+size 4991255560

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647071ce21fb9f5e820c930434f261af8c07b193e81e1c776b6cf673edbb92c5
+size 4915910288

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84007abe64bb308bf19a8475bcf873e3f8d230a627da71735c66c0b11fb9efa5
+size 4999813128

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9348b22c318ba2172e23816547536bd84910f9276d9068a9098c12f63a4b337
+size 4999813120

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa4b97e44b1bd77a4e5287fb010393e5d3209b28eadcfe7035915d4e22e38c5
+size 4832007504

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20385900d1780ef76d19fd5579652de2e807b80d813d9385fb9bc21c7359b5d
+size 4999813096

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac69d3d4da8d996caeb1123f40f5ebf7018f1f62c1f06f28b658a823ebccd4aa
+size 2382465960

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c9c36c359e1617afef6f7583403567931b7b4f43f6552d2b2155a131650a2
+size 17209892