初始化项目，由ModelHub XC社区提供模型

Model: Shahansha/Manthan-1.5B Source: Original Platform
2026-04-22 13:19:58 +08:00
commit 23c99c3afa
14 changed files with 497 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen2.5-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
--- a/57
+++ b/57
@@ -0,0 +1,57 @@
+
+FROM Qwen2.5-1.5B-Instruct.Q8_0.gguf
+TEMPLATE """{{- if .Messages }}
+{{- if or .System .Tools }}<|im_start|>system
+{{- if .System }}
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+{{- end }}<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+{{ if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}<tool_call>
+{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{ end }}</tool_call>
+{{- end }}{{ if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<|endoftext|>"
+PARAMETER temperature 1.5
+PARAMETER min_p 0.1
+SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant."""
--- a/Qwen2.5-1.5B-Instruct.Q4_K_M.gguf
+++ b/Qwen2.5-1.5B-Instruct.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbdf4c6440ff2e9ef5a2794d48125043935622b8f60f27c84d8c83f9a62d06c
+size 986048000
--- a/Qwen2.5-1.5B-Instruct.Q8_0.gguf
+++ b/Qwen2.5-1.5B-Instruct.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcad84dc4cf2404ae91a65067e241915864b8dcd5a35dd876216b276de54695d
+size 1646572544
--- a/README.md
+++ b/README.md
@@ -0,0 +1,188 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+base_model_relation: finetune
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- genesis-agi
+- manthan
+- qwen2
+- tool-calling
+- agent
+- reasoning
+- grpo
+- qlora
+- chatml
+- smolagents
+datasets:
+- Shahansha/manthan-tool-reasoning-v1
+- glaiveai/glaive-function-calling-v2
+- NousResearch/hermes-function-calling-v1
+metrics:
+- accuracy
+- pass@1
+model-index:
+-
+    name: Manthan-1.5B
+    results:
+    -
+        task:
+            type: text-generation
+            name: Tool-Augmented Generation
+        dataset:
+            name: GSM8K
+            type: gsm8k
+        metrics:
+        -
+            name: Tool-Augmented Accuracy
+            type: accuracy
+            value: 65.0
+    -
+        task:
+            type: text-generation
+            name: Code Generation
+        dataset:
+            name: MBPP
+            type: mbpp
+        metrics:
+        -
+            name: pass@1
+            type: pass@1
+            value: 50.0
+---
+
+# Genesis Manthan - 1.5B
+
+Genesis Manthan is a small language model fine-tuned to reason through tool interaction instead of verbal chain-of-thought. It is built on top of Qwen2.5-1.5B-Instruct and tuned for tool-first responses, agent workflows, and smolagents-style execution loops.
+
+## Model Summary
+
+- Base model: `Qwen/Qwen2.5-1.5B-Instruct`
+- Published model: `Shahansha/Manthan-1.5B`
+- Training recipe: QLoRA SFT -> GRPO with tool-execution rewards -> budget forcing at inference time
+- Primary behavior: emit structured tool calls before final answers
+- Intended ecosystem: Hugging Face Transformers, Gradio Spaces, smolagents, local agent runners
+
+## Why this model exists
+
+Most small open models still answer by generating verbose text, even when the task would be better solved through an external tool. Manthan is designed around a different behavior: call a tool, observe the result, and then answer. The target is not hidden verbal reasoning. The target is reliable action traces that small models can actually execute.
+
+spaces:
+  - Shahansha/Manthan-Demo
+    
+## Benchmark Snapshot
+
+| Benchmark | Metric | Reported Result |
+|---|---:|---:|
+| GSM8K | Tool-augmented accuracy | 65.0 |
+| MBPP | pass@1 | 50.0 |
+
+*Reported benchmark numbers are early project metrics and should be independently reproduced before strong claims are made.
+
+## Quickstart
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "Shahansha/Manthan-1.5B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    dtype=torch.float16,
+    device_map="auto",
+)
+model.generation_config.max_length = None
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You are Genesis Manthan, an AI agent that solves problems by calling tools. "
+            "Never reason verbally - always reason through tool execution."
+        ),
+    },
+    {"role": "user", "content": "What is 144 + 256?"},
+]
+
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.2,
+)
+
+print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
+```
+
+Expected behavior: the completion should include a `<tool_call>` block before the final answer.
+
+## Prompting Guidance
+
+This model performs best when the system prompt explicitly instructs it to solve problems by calling tools. If you omit that instruction, it may drift back toward plain-text assistant behavior.
+
+Recommended system message:
+
+```text
+You are Genesis Manthan, an AI agent that solves problems by calling tools. Never reason verbally - always reason through tool execution.
+```
+
+## Training Details
+
+- Base checkpoint: `Qwen/Qwen2.5-1.5B-Instruct`
+- Fine-tuning method: QLoRA SFT
+- Reinforcement learning: GRPO with composable rewards for tool execution, answer correctness, and format compliance
+- Data format: ChatML with custom tool roles and structured `<tool_call>` blocks
+- Primary training data: `Shahansha/manthan-tool-reasoning-v1` plus function-calling traces derived from Glaive and Hermes datasets
+
+## Intended Use
+
+- Agentic math and reasoning tasks where external execution is available
+- Tool-augmented code and debugging workflows
+- Research experiments around small-model tool use
+- Gradio demos and Hugging Face Spaces showcasing action-first reasoning
+
+## Limitations
+
+- This is a research model, not a general factual authority
+- Reported benchmark numbers are early project metrics and should be independently reproduced before strong claims are made
+- The model relies heavily on the surrounding prompt and tool scaffolding
+- Small models can still emit malformed tool calls or conclude too early without budget forcing or downstream validation
+
+## Safety and Responsible Use
+
+- Do not treat tool-call output as inherently safe to execute without sandboxing
+- Validate JSON arguments and restrict available tools in production
+- Review outputs carefully in coding, shell, or data-execution environments
+- This model was not trained for high-stakes legal, medical, or safety-critical decisions
+
+## Project Links
+
+- Model: https://huggingface.co/Shahansha/Manthan-1.5B
+- Dataset: https://huggingface.co/datasets/Shahansha/manthan-tool-reasoning-v1
+- Code: https://github.com/shaik-shahansha/manthan
+- Deployment guide: https://github.com/shaik-shahansha/manthan/blob/main/docs/HUGGINGFACE_DEPLOY.md
+- Author: https://shahansha.com
+- Org: https://genesisagi.in
+
+## Citation
+
+```bibtex
+@misc{shaik2026manthan,
+    title={Genesis Manthan-1.5B: Tool-Mediated Reasoning for Small Language Models},
+    author={Shahansha Shaik},
+    year={2026},
+    url={https://huggingface.co/Shahansha/Manthan-1.5B}
+}
+```
+
+---
--- a/adapter_config.json
+++ b/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/adapter_model.safetensors
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1e5740a20d4169c5a3f10aa6d90ffc4228085d7633c494c06d55f349e19ef2
+size 73911112
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,62 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "torch_dtype": "float16",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "max_window_layers": 21,
+    "model_type": "qwen2",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "rope_theta": 1000000.0,
+        "rope_type": "default"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.4",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,14 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151654,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.5.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82b8d498f2c6ddcc2cf02429d5dfe1c9666e62720b30edee3ad90b5653baace
+size 3087467144
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abbf42c330406a916ff5046127fb1d84fcc066dcaea8401b2b2782cd6941c04a
+size 6737