commit 69e5d98bd9e45e0ec543b6f836a91149c37a62b5 Author: ModelHub XC Date: Thu Jun 25 23:34:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: kmaurinjones/grammar-llama-3.2-1B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ea95ce2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +model.F16.gguf filter=lfs diff=lfs merge=lfs -text +model.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +model.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +model.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +grammar-llama-3.2-1B.F16.gguf filter=lfs diff=lfs merge=lfs -text +grammar-llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grammar-llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +grammar-llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..cdf46b8 --- /dev/null +++ b/Modelfile @@ -0,0 +1,57 @@ + +FROM /content/kmaurinjones/grammar-llama-3.2-1B/grammar-llama-3.2-1B.F16.gguf +TEMPLATE """{{ if .Messages }} +{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> +{{- if .System }} + +{{ .System }} +{{- end }} +{{- if .Tools }} + +You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question. +{{- end }} +{{- end }}<|eot_id|> +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|> +{{- if and $.Tools $last }} + +Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt. + +Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables. + +{{ $.Tools }} +{{- end }} + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|> +{{- if .ToolCalls }} + +{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }} +{{- else }} + +{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }} +{{- end }} +{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|> + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- end }} +{{- end }} +{{- else }} +{{- if .System }}<|start_header_id|>system<|end_header_id|> + +{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> + +{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}""" +PARAMETER stop "<|start_header_id|>" +PARAMETER stop "<|end_header_id|>" +PARAMETER stop "<|eot_id|>" +PARAMETER stop "<|eom_id|>" +PARAMETER temperature 1.5 +PARAMETER min_p 0.1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..09e72e4 --- /dev/null +++ b/README.md @@ -0,0 +1,118 @@ +--- +base_model: +- unsloth/Llama-3.2-1B-Instruct-bnb-4bit +- meta-llama/Llama-3.2-1B +tags: +- text-generation-inference +- transformers +- llama +- gguf +license: apache-2.0 +language: +- en +--- + +![Grammar Llama Model](grammar-llama.webp) + +# Uploaded model + +- **Developed by:** kmaurinjones +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/Llama-3.2-1B-Instruct-bnb-4bit + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "kmaurinjones/grammar-llama-3.2-1B" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +messages = [ + { + "role": "system", + "content": "", + }, + { + "role": "user", + "content": """ + # Instructions + - Revise the following transcript in the ways outlined below + - Return exactly the revised text and nothing else + - Use the custom vocabulary of terms to inform your revision + + # Revisions + - Correct grammar + - Correct punctuation + - Correct spelling + - Correct word choice + + # Vocabulary + {custom vocabulary terms, separated by newline} + + # Transcript + {transcript} + """ + } +] + +input_ids = tokenizer.apply_chat_template( + messages, + add_generation_prompt=True, + return_tensors="pt" +).to(model.device) + +terminators = [ + tokenizer.eos_token_id, + tokenizer.convert_tokens_to_ids("<|eot_id|>") +] + +outputs = model.generate( + input_ids, + # max_new_tokens=256, + eos_token_id=terminators, + do_sample=True, + temperature=0.1, +) +response = outputs[0] +print(tokenizer.decode(response)) + +# Example of Model Input +""" +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +Cutting Knowledge Date: December 2023 +Today Date: 26 July 2024 + +<|eot_id|><|start_header_id|>user<|end_header_id|> + +# Instructions +- Revise the following transcript in the ways outlined below +- Return exactly the revised text and nothing else +- Use the custom vocabulary of terms to inform your revision + +# Revisions +- Correct grammar +- Correct punctuation +- Correct spelling +- Correct word choice + +# Vocabulary +Seljukid +Turbessel +Gaziantep +Ahlat + +# Transcript +in 1111, he was invited to participate in a seljookid campaign. with his troops he joined the main seljookid army. but during the siege of turbessle he died in august 1111. his coffin was sent to ahlat.<|eot_id|><|start_header_id|>assistant<|end_header_id|> +""" + +# Example of Model Output +""" +In 1111, he was invited to participate in a Seljukid campaign. With his troops he joined the main Seljukid army. But during the siege of Turbessel he died in August 1111. His coffin was sent to Ahlat.<|eot_id|> +""" +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/grammar-llama-3.2-1B.F16.gguf b/grammar-llama-3.2-1B.F16.gguf new file mode 100644 index 0000000..261cbf8 --- /dev/null +++ b/grammar-llama-3.2-1B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87aee7e9843c4f38f0eb4c1ced056f801e39abb1eabf9c5c320b0b8633497221 +size 2479595904 diff --git a/grammar-llama-3.2-1B.Q4_K_M.gguf b/grammar-llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..9a5319f --- /dev/null +++ b/grammar-llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12371ba321df05a8c9617ff01941b334853bf782f85fa0436b1d50097d5fee57 +size 807694720 diff --git a/grammar-llama-3.2-1B.Q5_K_M.gguf b/grammar-llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..a172b5e --- /dev/null +++ b/grammar-llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80512819e162dd6feddbbf15bd5a931cfd3feaeedcaae86cd98747df7cb1fa15 +size 911503744 diff --git a/grammar-llama-3.2-1B.Q8_0.gguf b/grammar-llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..307e956 --- /dev/null +++ b/grammar-llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7465f2d12ca3957b82e5443747eb83e624acea34460aeb154973a0b60f0ef42a +size 1321083264 diff --git a/grammar-llama.webp b/grammar-llama.webp new file mode 100644 index 0000000..00e8b61 Binary files /dev/null and b/grammar-llama.webp differ