初始化项目，由ModelHub XC社区提供模型

Model: tkeskin/llama-3.2-1b-instruct-code-translation Source: Original Platform
2026-07-18 06:26:09 +08:00
commit ee9d38ed1d
9 changed files with 309 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
--- a/15
+++ b/15
@@ -0,0 +1,15 @@
+# ollama modelfile auto-generated by llamafactory
+
+FROM .
+
+TEMPLATE """<|begin_of_text|>{{ if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Content }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+{{ else if eq .Role "assistant" }}{{ .Content }}<|eot_id|>{{ end }}{{ end }}"""
+
+PARAMETER stop "<|eom_id|>"
+PARAMETER stop "<|eot_id|>"
+PARAMETER num_ctx 4096
--- a/README.md
+++ b/README.md
@@ -0,0 +1,87 @@
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+license: llama3.2
+datasets:
+  - tkeskin/leetcode-solutions
+language:
+  - en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - lora
+  - llama-factory
+  - code
+  - code-translation
+  - llama
+---
+
+# llama-3.2-1b-instruct-code-translation
+
+A fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) for translating code between **C++**, **Java**, and **Python**.
+
+## Training
+
+- **Base model:** meta-llama/Llama-3.2-1B-Instruct
+- **Method:** LoRA (Low-Rank Adaptation) via [LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory)
+- **Dataset:** [tkeskin/leetcode-solutions](https://huggingface.co/datasets/tkeskin/leetcode-solutions) (`instruct` config) — directed C++/Java/Python translation pairs derived from LeetCode solutions
+- **Hardware:** AMD MI210 (ROCm) / NVIDIA CUDA, `flash_attn: sdpa`
+- **LoRA target:** all linear layers (`lora_target: all`)
+- **Precision:** bf16
+
+## Evaluation
+
+Evaluated with an **execution-based** translation benchmark: each held-out `evaluation`-config payload from [tkeskin/leetcode-solutions](https://huggingface.co/datasets/tkeskin/leetcode-solutions) is a directed source→target translation whose output is compiled and run against the problem's input/output pairs. The eval split is held out from training (no leakage). Metric is **pass@1** (all test cases pass), n-weighted over 3,336 payloads.
+
+| | Base (Llama-3.2-1B-Instruct) | This model | Δ |
+|---|---|---|---|
+| **pass@1** | 17.5% | **32.5%** | **+15.0** |
+| **compile rate** | 52.8% | **72.7%** | **+19.8** |
+
+pass@1 by language pair × difficulty (%):
+
+| source | target | difficulty | base | this model |
+|---|---|---|---|---|
+| cpp | java | Easy | 29.0 | 55.9 |
+| cpp | java | Hard | 7.6 | 24.6 |
+| cpp | java | Medium | 15.9 | 39.5 |
+| cpp | python | Easy | 32.0 | 37.2 |
+| cpp | python | Hard | 10.7 | 17.6 |
+| cpp | python | Medium | 24.4 | 33.8 |
+| java | cpp | Easy | 15.0 | 61.2 |
+| java | cpp | Hard | 4.2 | 27.7 |
+| java | cpp | Medium | 14.4 | 44.4 |
+| java | python | Easy | 31.4 | 44.8 |
+| java | python | Hard | 13.0 | 22.9 |
+| java | python | Medium | 19.2 | 31.8 |
+| python | cpp | Easy | 23.8 | 40.1 |
+| python | cpp | Hard | 1.7 | 6.7 |
+| python | cpp | Medium | 15.6 | 23.3 |
+| python | java | Easy | 24.1 | 30.3 |
+| python | java | Hard | 3.4 | 7.6 |
+| python | java | Medium | 12.4 | 19.4 |
+
+Full methodology is in the [llm-fine-tune](https://github.com/tkeskin/llm-fine-tune) repo (Stage 5).
+
+## Intended use
+
+Given source code in one of C++, Java, or Python, the model generates a translation into the target language, following the same logic and structure.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "tkeskin/llama-3.2-1b-instruct-code-translation"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+messages = [
+    {
+        "role": "user",
+        "content": "Translate the following C++ code to Python:\n\nint add(int a, int b) { return a + b; }"
+    }
+]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
+outputs = model.generate(inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.6.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}
--- a/generation_config.json
+++ b/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": "5.6.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd201c9031c9d5156e959933d342d7dbe101dff8d353dac3a6019848dc235a5
+size 2471645608
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}